GCVE Workshop - 22 September 2026 (14:00-18:00), Luxembourg Before The Vulnopticon Conference - Registration
Common Weakness Enumeration

CWE-668

Discouraged

Exposure of Resource to Wrong Sphere

Abstraction: Class · Status: Draft

API response cwe.mitre.org

The product exposes a resource to the wrong control sphere, providing unintended actors with inappropriate access to the resource.

1276 vulnerabilities reference this CWE, most recent first.

GHSA-75XQ-8H5M-HRPV

Vulnerability from github – Published: 2022-11-04 12:00 – Updated: 2022-11-04 19:01
VLAI
Details

"IBM InfoSphere Information Server 11.7 could allow an authenticated user to access information restricted to users with elevated privileges due to improper access controls. IBM X-Force ID: 224427."

Severity
6.5 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2022-22442"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-284",
      "CWE-668"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2022-11-03T20:15:00Z",
    "severity": "MODERATE"
  },
  "details": "\"IBM InfoSphere Information Server 11.7 could allow an authenticated user to access information restricted to users with elevated privileges due to improper access controls. IBM X-Force ID: 224427.\"",
  "id": "GHSA-75xq-8h5m-hrpv",
  "modified": "2022-11-04T19:01:16Z",
  "published": "2022-11-04T12:00:24Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2022-22442"
    },
    {
      "type": "WEB",
      "url": "https://www.ibm.com/support/pages/node/6829325"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-766V-Q9X3-G744

Vulnerability from github – Published: 2026-04-08 19:21 – Updated: 2026-06-19 21:33
VLAI
Summary
PraisonAI has Memory State Leakage and Path Traversal in MultiAgent Context Handling
Details

Summary

The MultiAgentLedger and MultiAgentMonitor components in the provided code exhibit vulnerabilities that can lead to context leakage and arbitrary file operations. Specifically: 1. Memory State Leakage via Agent ID Collision: The MultiAgentLedger uses a dictionary to store ledgers by agent ID without enforcing uniqueness. This allows agents with the same ID to share ledger instances, leading to potential leakage of sensitive context data. 2. Path Traversal in MultiAgentMonitor: The MultiAgentMonitor constructs file paths by concatenating the base_path and agent ID without sanitization. This allows an attacker to escape the intended directory using path traversal sequences (e.g., ../), potentially leading to arbitrary file read/write.

Details

Vulnerability 1: Memory State Leakage

  • File: examples/context/12_multi_agent_context.py:68
  • Description: The MultiAgentLedger class uses a dictionary (self.ledgers) to store ledger instances keyed by agent ID. The get_agent_ledger method creates a new ledger only if the agent ID is not present. If two agents are registered with the same ID, they will share the same ledger instance. This violates the isolation policy and can lead to leakage of sensitive context data (system prompts, conversation history) between agents.
  • Exploitability: An attacker can register an agent with the same ID as a victim agent to gain access to their ledger. This is particularly dangerous in multi-tenant systems where agents may handle sensitive user data.

Vulnerability 2: Path Traversal

  • File: examples/context/12_multi_agent_context.py:106
  • Description: The MultiAgentMonitor class constructs file paths for agent monitors by directly concatenating the base_path and agent ID. Since the agent ID is not sanitized, an attacker can provide an ID containing path traversal sequences (e.g., ../../malicious). This can result in files being created or read outside the intended directory (base_path).
  • Exploitability: An attacker can create an agent with a malicious ID (e.g., ../../etc/passwd) to write or read arbitrary files on the system, potentially leading to information disclosure or file corruption.

PoC

Memory State Leakage

multi_ledger = MultiAgentLedger()

# Victim agent (user1) registers and tracks sensitive data
victim_ledger = multi_ledger.get_agent_ledger('user1_agent')
victim_ledger.track_system_prompt("Sensitive system prompt")
victim_ledger.track_history([{"role": "user", "content": "Secret data"}])

# Attacker registers with the same ID
attacker_ledger = multi_ledger.get_agent_ledger('user1_agent')

# Attacker now has access to victim's ledger
print(attacker_ledger.get_ledger().system_prompt)  # Outputs: "Sensitive system prompt"
print(attacker_ledger.get_ledger().history)        # Outputs: [{'role': 'user', 'content': 'Secret data'}]

Path Traversal

with tempfile.TemporaryDirectory() as tmpdir:
    multi_monitor = MultiAgentMonitor(base_path=tmpdir)

    # Create agent with malicious ID
    malicious_id = '../../malicious'
    monitor = multi_monitor.get_agent_monitor(malicious_id)

    # The monitor file is created outside the intended base_path
    # Example: if tmpdir is '/tmp/safe_dir', the actual path might be '/tmp/malicious'
    print(monitor.path)  # Outputs: '/tmp/malicious' (or equivalent)

Impact

  • Memory State Leakage: This vulnerability can lead to unauthorized access to sensitive agent context, including system prompts and conversation history. In a multi-tenant system, this could result in cross-user data leakage.
  • Path Traversal: An attacker can read or write arbitrary files on the system, potentially leading to information disclosure, denial of service (by overwriting critical files), or remote code execution (if executable files are overwritten).

Recommended Fix

For Memory State Leakage

  • Enforce unique agent IDs at the application level. If the application expects unique IDs, add a check during agent registration to prevent duplicates.
  • Alternatively, modify the MultiAgentLedger to throw an exception if an existing agent ID is reused (unless explicitly allowed).

For Path Traversal

  • Sanitize agent IDs before using them in file paths. Replace any non-alphanumeric characters (except safe ones like underscores) or remove path traversal sequences.
  • Use os.path.join and os.path.realpath to resolve paths, then check that the resolved path starts with the intended base directory.

Example fix for MultiAgentMonitor:

import os

def get_agent_monitor(self, agent_id: str):
    # Sanitize agent_id to remove path traversal
    safe_id = os.path.basename(agent_id.replace('../', '').replace('..\\', ''))
    # Alternatively, use a strict allow-list of characters

    # Construct path and ensure it's within base_path
    agent_path = os.path.join(self.base_path, safe_id)
    real_path = os.path.realpath(agent_path)
    real_base = os.path.realpath(self.base_path)

    if not real_path.startswith(real_base):
        raise ValueError(f"Invalid agent ID: {agent_id}")

    ...

Additionally, consider using a dedicated function for sanitizing filenames.

Severity
6.5 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "database_specific": {
        "last_known_affected_version_range": "\u003c= 1.5.114"
      },
      "package": {
        "ecosystem": "PyPI",
        "name": "praisonaiagents"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.5.115"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-56078"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-22",
      "CWE-668"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-08T19:21:32Z",
    "nvd_published_at": null,
    "severity": "MODERATE"
  },
  "details": "## Summary\nThe `MultiAgentLedger` and `MultiAgentMonitor` components in the provided code exhibit vulnerabilities that can lead to context leakage and arbitrary file operations. Specifically:\n1. **Memory State Leakage via Agent ID Collision**: The `MultiAgentLedger` uses a dictionary to store ledgers by agent ID without enforcing uniqueness. This allows agents with the same ID to share ledger instances, leading to potential leakage of sensitive context data.\n2. **Path Traversal in MultiAgentMonitor**: The `MultiAgentMonitor` constructs file paths by concatenating the `base_path` and agent ID without sanitization. This allows an attacker to escape the intended directory using path traversal sequences (e.g., `../`), potentially leading to arbitrary file read/write.\n\n## Details\n### Vulnerability 1: Memory State Leakage\n- **File**: `examples/context/12_multi_agent_context.py:68`\n- **Description**: The `MultiAgentLedger` class uses a dictionary (`self.ledgers`) to store ledger instances keyed by agent ID. The `get_agent_ledger` method creates a new ledger only if the agent ID is not present. If two agents are registered with the same ID, they will share the same ledger instance. This violates the isolation policy and can lead to leakage of sensitive context data (system prompts, conversation history) between agents.\n- **Exploitability**: An attacker can register an agent with the same ID as a victim agent to gain access to their ledger. This is particularly dangerous in multi-tenant systems where agents may handle sensitive user data.\n\n### Vulnerability 2: Path Traversal\n- **File**: `examples/context/12_multi_agent_context.py:106`\n- **Description**: The `MultiAgentMonitor` class constructs file paths for agent monitors by directly concatenating the `base_path` and agent ID. Since the agent ID is not sanitized, an attacker can provide an ID containing path traversal sequences (e.g., `../../malicious`). This can result in files being created or read outside the intended directory (`base_path`).\n- **Exploitability**: An attacker can create an agent with a malicious ID (e.g., `../../etc/passwd`) to write or read arbitrary files on the system, potentially leading to information disclosure or file corruption.\n\n## PoC\n### Memory State Leakage\n```python\nmulti_ledger = MultiAgentLedger()\n\n# Victim agent (user1) registers and tracks sensitive data\nvictim_ledger = multi_ledger.get_agent_ledger(\u0027user1_agent\u0027)\nvictim_ledger.track_system_prompt(\"Sensitive system prompt\")\nvictim_ledger.track_history([{\"role\": \"user\", \"content\": \"Secret data\"}])\n\n# Attacker registers with the same ID\nattacker_ledger = multi_ledger.get_agent_ledger(\u0027user1_agent\u0027)\n\n# Attacker now has access to victim\u0027s ledger\nprint(attacker_ledger.get_ledger().system_prompt)  # Outputs: \"Sensitive system prompt\"\nprint(attacker_ledger.get_ledger().history)        # Outputs: [{\u0027role\u0027: \u0027user\u0027, \u0027content\u0027: \u0027Secret data\u0027}]\n```\n\n### Path Traversal\n```python\nwith tempfile.TemporaryDirectory() as tmpdir:\n    multi_monitor = MultiAgentMonitor(base_path=tmpdir)\n    \n    # Create agent with malicious ID\n    malicious_id = \u0027../../malicious\u0027\n    monitor = multi_monitor.get_agent_monitor(malicious_id)\n    \n    # The monitor file is created outside the intended base_path\n    # Example: if tmpdir is \u0027/tmp/safe_dir\u0027, the actual path might be \u0027/tmp/malicious\u0027\n    print(monitor.path)  # Outputs: \u0027/tmp/malicious\u0027 (or equivalent)\n```\n\n## Impact\n- **Memory State Leakage**: This vulnerability can lead to unauthorized access to sensitive agent context, including system prompts and conversation history. In a multi-tenant system, this could result in cross-user data leakage.\n- **Path Traversal**: An attacker can read or write arbitrary files on the system, potentially leading to information disclosure, denial of service (by overwriting critical files), or remote code execution (if executable files are overwritten).\n\n## Recommended Fix\n### For Memory State Leakage\n- Enforce unique agent IDs at the application level. If the application expects unique IDs, add a check during agent registration to prevent duplicates.\n- Alternatively, modify the `MultiAgentLedger` to throw an exception if an existing agent ID is reused (unless explicitly allowed).\n\n### For Path Traversal\n- Sanitize agent IDs before using them in file paths. Replace any non-alphanumeric characters (except safe ones like underscores) or remove path traversal sequences.\n- Use `os.path.join` and `os.path.realpath` to resolve paths, then check that the resolved path starts with the intended base directory.\n\nExample fix for `MultiAgentMonitor`:\n```python\nimport os\n\ndef get_agent_monitor(self, agent_id: str):\n    # Sanitize agent_id to remove path traversal\n    safe_id = os.path.basename(agent_id.replace(\u0027../\u0027, \u0027\u0027).replace(\u0027..\\\\\u0027, \u0027\u0027))\n    # Alternatively, use a strict allow-list of characters\n    \n    # Construct path and ensure it\u0027s within base_path\n    agent_path = os.path.join(self.base_path, safe_id)\n    real_path = os.path.realpath(agent_path)\n    real_base = os.path.realpath(self.base_path)\n    \n    if not real_path.startswith(real_base):\n        raise ValueError(f\"Invalid agent ID: {agent_id}\")\n    \n    ...\n```\nAdditionally, consider using a dedicated function for sanitizing filenames.",
  "id": "GHSA-766v-q9x3-g744",
  "modified": "2026-06-19T21:33:34Z",
  "published": "2026-04-08T19:21:32Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-766v-q9x3-g744"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-56078"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/MervinPraison/PraisonAI"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/praisonai-arbitrary-file-read-and-write-via-path-traversal-in-multiagentmonitor"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "PraisonAI has Memory State Leakage and Path Traversal in MultiAgent Context Handling"
}

GHSA-76Q4-6GM8-M28C

Vulnerability from github – Published: 2022-05-13 01:03 – Updated: 2022-05-13 01:03
VLAI
Details

General Electric (GE) Digital Proficy HMI/SCADA - CIMPLICITY before 8.2 SIM 27 mishandles service DACLs, which allows local users to modify a service configuration via unspecified vectors.

Severity
6.3 (Medium)
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:L
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2016-5787"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-668"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2016-07-15T16:59:00Z",
    "severity": "MODERATE"
  },
  "details": "General Electric (GE) Digital Proficy HMI/SCADA - CIMPLICITY before 8.2 SIM 27 mishandles service DACLs, which allows local users to modify a service configuration via unspecified vectors.",
  "id": "GHSA-76q4-6gm8-m28c",
  "modified": "2022-05-13T01:03:59Z",
  "published": "2022-05-13T01:03:59Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2016-5787"
    },
    {
      "type": "WEB",
      "url": "https://ge-ip.force.com/communities/en_US/Article/GE-Digital-Security-Advisory-GED-16-01"
    },
    {
      "type": "WEB",
      "url": "https://ics-cert.us-cert.gov/advisories/ICSA-16-194-02"
    },
    {
      "type": "WEB",
      "url": "http://www.securityfocus.com/bid/91727"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:L/I:L/A:L",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-76R9-Q8J4-X44W

Vulnerability from github – Published: 2023-01-26 21:30 – Updated: 2023-02-01 18:30
VLAI
Details

Qlik QlikView through 12.60.20100.0 creates a Temporary File in a Directory with Insecure Permissions.

Severity
7.8 (High)
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2021-41989"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-668"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2023-01-26T21:15:00Z",
    "severity": "HIGH"
  },
  "details": "Qlik QlikView through 12.60.20100.0 creates a Temporary File in a Directory with Insecure Permissions.",
  "id": "GHSA-76r9-q8j4-x44w",
  "modified": "2023-02-01T18:30:31Z",
  "published": "2023-01-26T21:30:29Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2021-41989"
    },
    {
      "type": "WEB",
      "url": "https://github.com/mandiant/Vulnerability-Disclosures/blob/master/2023/MNDT-2023-0001.md"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-773V-8W82-H42V

Vulnerability from github – Published: 2022-05-24 17:48 – Updated: 2022-07-13 00:01
VLAI
Details

An issue was discovered in the AbuseFilter extension for MediaWiki through 1.35.2. A MediaWiki user who is partially blocked or was unsuccessfully blocked could bypass AbuseFilter and have their edits completed.

Severity
6.5 (Medium)
CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2021-31548"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-668"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2021-04-22T03:15:00Z",
    "severity": "MODERATE"
  },
  "details": "An issue was discovered in the AbuseFilter extension for MediaWiki through 1.35.2. A MediaWiki user who is partially blocked or was unsuccessfully blocked could bypass AbuseFilter and have their edits completed.",
  "id": "GHSA-773v-8w82-h42v",
  "modified": "2022-07-13T00:01:24Z",
  "published": "2022-05-24T17:48:07Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2021-31548"
    },
    {
      "type": "WEB",
      "url": "https://gerrit.wikimedia.org/r/q/Ifac795125927d584a31d95e1b4c4241eef860fa1"
    },
    {
      "type": "WEB",
      "url": "https://phabricator.wikimedia.org/T272333"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:H/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-77F7-R2CC-PCQM

Vulnerability from github – Published: 2022-05-24 17:37 – Updated: 2022-05-24 17:37
VLAI
Details

Improper access control in mail module (followers) in Odoo Community 13.0 and earlier and Odoo Enterprise 13.0 and earlier, allows remote authenticated users to obtain access to messages posted on business records there were not given access to, and subscribe to receive future messages.

Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2019-11785"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-668",
      "CWE-862"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2020-12-22T17:15:00Z",
    "severity": "MODERATE"
  },
  "details": "Improper access control in mail module (followers) in Odoo Community 13.0 and earlier and Odoo Enterprise 13.0 and earlier, allows remote authenticated users to obtain access to messages posted on business records there were not given access to, and subscribe to receive future messages.",
  "id": "GHSA-77f7-r2cc-pcqm",
  "modified": "2022-05-24T17:37:00Z",
  "published": "2022-05-24T17:37:00Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2019-11785"
    },
    {
      "type": "WEB",
      "url": "https://github.com/odoo/odoo/issues/63710"
    }
  ],
  "schema_version": "1.4.0",
  "severity": []
}

GHSA-77G3-3J5W-64W4

Vulnerability from github – Published: 2021-04-07 20:36 – Updated: 2024-09-06 20:16
VLAI
Summary
Exposure of Resource to Wrong Sphere and Insecure Temporary File in Ansible
Details

A flaw was found in Ansible Engine affecting Ansible Engine versions 2.7.x before 2.7.17 and 2.8.x before 2.8.11 and 2.9.x before 2.9.7 as well as Ansible Tower before and including versions 3.4.5 and 3.5.5 and 3.6.3 when using modules which decrypts vault files such as assemble, script, unarchive, win_copy, aws_s3 or copy modules. The temporary directory is created in /tmp leaves the s ts unencrypted. On Operating Systems which /tmp is not a tmpfs but part of the root partition, the directory is only cleared on boot and the decryp emains when the host is switched off. The system will be vulnerable when the system is not running. So decrypted data must be cleared as soon as possible and the data which normally is encrypted ble.

Severity
5.5 (Medium)
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
6.8 (Medium)
CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N
Show details on source website
To clipboard 

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "ansible"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.7.0a1"
            },
            {
              "fixed": "2.7.17"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "ansible"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.8.0a1"
            },
            {
              "fixed": "2.8.11"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    },
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "ansible"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "2.9.0a1"
            },
            {
              "fixed": "2.9.7"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2020-10685"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-377",
      "CWE-459",
      "CWE-668"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2021-04-05T14:11:30Z",
    "nvd_published_at": "2020-05-11T14:15:00Z",
    "severity": "MODERATE"
  },
  "details": "A flaw was found in Ansible Engine affecting Ansible Engine versions 2.7.x before 2.7.17 and 2.8.x before 2.8.11 and 2.9.x before 2.9.7 as well as Ansible Tower before and including versions 3.4.5 and 3.5.5 and 3.6.3 when using modules which decrypts vault files such as assemble, script, unarchive, win_copy, aws_s3 or copy modules. The temporary directory is created in /tmp leaves the s ts unencrypted. On Operating Systems which /tmp is not a tmpfs but part of the root partition, the directory is only cleared on boot and the decryp emains when the host is switched off. The system will be vulnerable when the system is not running. So decrypted data must be cleared as soon as possible and the data which normally is encrypted ble.",
  "id": "GHSA-77g3-3j5w-64w4",
  "modified": "2024-09-06T20:16:43Z",
  "published": "2021-04-07T20:36:46Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2020-10685"
    },
    {
      "type": "WEB",
      "url": "https://github.com/ansible/ansible/pull/68433"
    },
    {
      "type": "WEB",
      "url": "https://github.com/ansible/ansible/commit/4e1fe80e681fa466626e9dea53efe6b0253ea1b2"
    },
    {
      "type": "WEB",
      "url": "https://github.com/ansible/ansible/commit/51d2514753544a9d58cd7524e27e696b2c944fb5"
    },
    {
      "type": "WEB",
      "url": "https://github.com/ansible/ansible/commit/e1273b6faf036ed84e4f4edee85b888a4e256aee"
    },
    {
      "type": "WEB",
      "url": "https://bugzilla.redhat.com/show_bug.cgi?id=CVE-2020-10685"
    },
    {
      "type": "ADVISORY",
      "url": "https://github.com/advisories/GHSA-77g3-3j5w-64w4"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/ansible/ansible"
    },
    {
      "type": "WEB",
      "url": "https://github.com/pypa/advisory-database/tree/main/vulns/ansible/PYSEC-2020-1.yaml"
    },
    {
      "type": "WEB",
      "url": "https://security.gentoo.org/glsa/202006-11"
    },
    {
      "type": "WEB",
      "url": "https://www.debian.org/security/2021/dsa-4950"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    },
    {
      "score": "CVSS:4.0/AV:L/AC:L/AT:N/PR:L/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N",
      "type": "CVSS_V4"
    }
  ],
  "summary": "Exposure of Resource to Wrong Sphere and Insecure Temporary File in Ansible"
}

GHSA-785W-VJ78-P44X

Vulnerability from github – Published: 2022-02-10 00:00 – Updated: 2026-07-05 03:30
VLAI
Details

Thinfinity VirtualUI 2.1.28.0, 2.1.32.1 and 2.5.26.2, fixed in version 3.0 is affected by an information disclosure vulnerability in the parameter "Addr" in cmd site. The ability to send requests to other systems can allow the vulnerable server to filtrate the real IP of the web server or increase the attack surface.

Severity
7.5 (High)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2021-46354"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-668"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2022-02-09T14:15:00Z",
    "severity": "HIGH"
  },
  "details": "Thinfinity VirtualUI 2.1.28.0, 2.1.32.1 and 2.5.26.2, fixed in version 3.0 is affected by an information disclosure vulnerability in the parameter \"Addr\" in cmd site. The ability to send requests to other systems can allow the vulnerable server to filtrate the real IP of the web server or increase the attack surface.",
  "id": "GHSA-785w-vj78-p44x",
  "modified": "2026-07-05T03:30:44Z",
  "published": "2022-02-10T00:00:30Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2021-46354"
    },
    {
      "type": "WEB",
      "url": "https://github.com/cybelesoft/virtualui/issues/3"
    },
    {
      "type": "WEB",
      "url": "http://packetstormsecurity.com/files/166069/Thinfinity-VirtualUI-2.5.26.2-Information-Disclosure.html"
    },
    {
      "type": "WEB",
      "url": "http://thinfinity.com"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ]
}

GHSA-78XP-FCVC-XXJX

Vulnerability from github – Published: 2022-05-24 17:01 – Updated: 2022-05-24 17:01
VLAI
Details

The Tecno Camon Android device with a build fingerprint of TECNO/H612/TECNO-ID5a:8.1.0/O11019/F-180828V106:user/release-keys contains a pre-installed platform app with a package name of com.lovelyfont.defcontainer (versionCode=7, versionName=7.0.11). This app contains an exported service named com.lovelyfont.manager.service.FunctionService that allows any app co-located on the device to supply the file path to a Dalvik Executable (DEX) file which it will dynamically load within its own process and execute in with its own system privileges. This app cannot be disabled by the user and the attack can be performed by a zero-permission app. Executing commands as the system user can allow a third-party app to video record the user's screen, factory reset the device, obtain the user's notifications, read the logcat logs, inject events in the Graphical User Interface (GUI), and obtains the user's text messages, and more. Executing code as the system user can allow a third-party app to factory reset the device, obtain the user's Wi-Fi passwords, obtain the user's notifications, read the logcat logs, inject events in the GUI, change the default Input Method Editor (IME) (e.g., keyboard) with one contained within the attacking app that contains keylogging functionality, and obtains the user's text messages, and more.

Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2019-15349"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-668"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2019-11-14T17:15:00Z",
    "severity": "HIGH"
  },
  "details": "The Tecno Camon Android device with a build fingerprint of TECNO/H612/TECNO-ID5a:8.1.0/O11019/F-180828V106:user/release-keys contains a pre-installed platform app with a package name of com.lovelyfont.defcontainer (versionCode=7, versionName=7.0.11). This app contains an exported service named com.lovelyfont.manager.service.FunctionService that allows any app co-located on the device to supply the file path to a Dalvik Executable (DEX) file which it will dynamically load within its own process and execute in with its own system privileges. This app cannot be disabled by the user and the attack can be performed by a zero-permission app. Executing commands as the system user can allow a third-party app to video record the user\u0027s screen, factory reset the device, obtain the user\u0027s notifications, read the logcat logs, inject events in the Graphical User Interface (GUI), and obtains the user\u0027s text messages, and more. Executing code as the system user can allow a third-party app to factory reset the device, obtain the user\u0027s Wi-Fi passwords, obtain the user\u0027s notifications, read the logcat logs, inject events in the GUI, change the default Input Method Editor (IME) (e.g., keyboard) with one contained within the attacking app that contains keylogging functionality, and obtains the user\u0027s text messages, and more.",
  "id": "GHSA-78xp-fcvc-xxjx",
  "modified": "2022-05-24T17:01:02Z",
  "published": "2022-05-24T17:01:02Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2019-15349"
    },
    {
      "type": "WEB",
      "url": "https://www.kryptowire.com/android-firmware-2019"
    }
  ],
  "schema_version": "1.4.0",
  "severity": []
}

GHSA-79CC-R4HF-5PV4

Vulnerability from github – Published: 2024-02-27 09:31 – Updated: 2024-04-10 15:30
VLAI
Details

In the Linux kernel, the following vulnerability has been resolved:

dmaengine: idxd: fix wq cleanup of WQCFG registers

A pre-release silicon erratum workaround where wq reset does not clear WQCFG registers was leaked into upstream code. Use wq reset command instead of blasting the MMIO region. This also address an issue where we clobber registers in future devices.

Severity
5.5 (Medium)
CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N
Show details on source website
To clipboard 

{
  "affected": [],
  "aliases": [
    "CVE-2021-46917"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-668"
    ],
    "github_reviewed": false,
    "github_reviewed_at": null,
    "nvd_published_at": "2024-02-27T07:15:08Z",
    "severity": "MODERATE"
  },
  "details": "In the Linux kernel, the following vulnerability has been resolved:\n\ndmaengine: idxd: fix wq cleanup of WQCFG registers\n\nA pre-release silicon erratum workaround where wq reset does not clear\nWQCFG registers was leaked into upstream code. Use wq reset command\ninstead of blasting the MMIO region. This also address an issue where\nwe clobber registers in future devices.",
  "id": "GHSA-79cc-r4hf-5pv4",
  "modified": "2024-04-10T15:30:31Z",
  "published": "2024-02-27T09:31:16Z",
  "references": [
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2021-46917"
    },
    {
      "type": "WEB",
      "url": "https://git.kernel.org/stable/c/e5eb9757fe4c2392e069246ae78badc573af1833"
    },
    {
      "type": "WEB",
      "url": "https://git.kernel.org/stable/c/ea9aadc06a9f10ad20a90edc0a484f1147d88a7a"
    },
    {
      "type": "WEB",
      "url": "https://git.kernel.org/stable/c/f7dc8f5619165e1fa3383d0c2519f502d9e2a1a9"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:N/A:N",
      "type": "CVSS_V3"
    }
  ]
}

No mitigation information available for this CWE.

No CAPEC attack patterns related to this CWE.

← Back to the CWE list