Vulnerability-Lookup

GHSA-6WJP-V33H-5CVQ

Vulnerability from github – Published: 2026-10-08 22:01 – Updated: 2026-10-08 22:01

Summary

PraisonAI: AgentOS defaults to network-exposed no-auth mode, allowing unauthenticated agent invocation and instruction disclosure

Details

Summary

The AgentOS server in the praisonai TypeScript/npm package ships an insecure default: it binds 0.0.0.0, sets no API key, and uses CORS * with credentials. The API-key middleware is only registered when an API key is configured, so the documented quickstart (new AgentOS({agents:[...]}).serve({port})) exposes, unauthenticated, GET /api/agents (which leaks agent names/roles/instructions, i.e. system prompts) and POST /api/chat (which invokes agents). Any network peer can read agent system prompts and drive the agent. Runtime-confirmed; severity High.

Details

Affected component

Package: praisonai (npm / TypeScript). Files src/praisonai-ts/src/os/config.ts and src/praisonai-ts/src/os/agentos.ts (AgentOS).

Vulnerable code / root cause

Path: src/praisonai-ts/src/os/config.ts

Class/const: DEFAULT_AGENTOS_CONFIG / mergeConfig

Snippet:

export const DEFAULT_AGENTOS_CONFIG = {
  host: '0.0.0.0',
  corsOrigins: ['*'],
  apiKey: '',
  // ...
};
// mergeConfig: apiKey = userConfig?.apiKey ?? process.env.PRAISONAI_AGENTOS_API_KEY ?? '';

Issue: defaults bind all interfaces, with an empty API key and wildcard CORS. apiKey stays empty unless the developer explicitly sets it.

Path: src/praisonai-ts/src/os/agentos.ts

Function: serve / _registerRoutes (Express app)

Snippet:

if (this.config.apiKey) {              // auth middleware ONLY added when apiKey is set
  app.use((req,res,next) => { /* 401 unless Bearer/x-auth-token matches */ });
}
// routes:
app.get(`${apiPrefix}/agents`, ...)    // returns name/role/instructions
app.post(`${apiPrefix}/chat`,  ...)    // calls agent.chat(message)

Issue: the only auth gate is conditional on a non-empty apiKey. With the default empty key, no auth middleware is registered, and GET /api/agents (system-prompt disclosure) and POST /api/chat (agent invocation) are served to any network client. CORS sets Access-Control-Allow-Credentials: true with a wildcard origin.

Attack flow

Developer deploys AgentOS via the quickstart without setting apiKey/PRAISONAI_AGENTOS_API_KEY.
Any network peer calls GET /api/agents → receives agent instructions/system prompts.
Any network peer calls POST /api/chat → invokes the agent.

Why existing protection is bypassed

There is no protection in the default config — the auth gate is skipped when apiKey is empty (the default), and the server binds all interfaces.

Security boundary

Unauthenticated network access to agent metadata + invocation. This is the CVE-2026-44338 anti-pattern recurring in the TS package, and worse (0.0.0.0 is the default).

Proof of Concept

Environment

Real AgentOS from src/praisonai-ts run via ts-node in a node container with default config (stub agent, no LLM needed). 127.0.0.1:18000. Runnable assets: PraisonAI-Runtime-Repro\runtime-files\ (docker-compose.agentos.yml).

Steps to reproduce

PRAI-01-01-AgentOS-Agents-NoAuth: GET /api/agents (no Authorization) → 127.0.0.1:18000.
PRAI-01-02-AgentOS-Chat-NoAuth: POST /api/chat {"message":"hello from attacker"} (no Authorization).

Expected result

Non-loopback exposure should require authentication; agent instructions should not be disclosed unauthenticated.

Actual result

GET /api/agents → 200, leaks "instructions":"SYSTEM PROMPT SECRET ... PRAISONAI_INTERNAL_SECRET_CANARY_7f3a91"; response header Access-Control-Allow-Credentials: true.
POST /api/chat → 200, agent invoked ("response":"...PRAISONAI_AGENTOS_CANARY_7f3a91...").

Screenshots

Unauthenticated /api/agents leaks agent instructions

A GET request to /api/agents succeeds without an Authorization header. The response exposes agent metadata and instructions, including the canary system-prompt value.

01-AgentOS-Agents-NoAuth

Unauthenticated /api/chat invokes the agent

A POST request to /api/chat succeeds without an Authorization header. The response confirms that the attacker-controlled message was processed by the configured agent.

02-AgentOS-Chat-NoAuth

Reproduction assets

The attached archive contains the local Docker runtime used to reproduce the issue with controlled canary values only. It does not contain real secrets, third-party API keys, or production credentials.

PraisonAI-Runtime-Repro.zip

Impact

Unauthenticated disclosure of agent configuration/system prompts; unauthenticated agent invocation; LLM cost abuse; possible tool abuse depending on the configured agent's tools; permissive CORS-with-credentials.

Suggested remediation

Default host to 127.0.0.1; require apiKey (fail closed) when binding non-loopback.
Do not default corsOrigins to ['*'], especially with Access-Control-Allow-Credentials: true.
Do not return full instructions on an unauthenticated endpoint.

Severity

8.6 (High)


                  
                    CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:L

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "npm",
        "name": "praisonai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.7.3"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-61426"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-200",
      "CWE-284",
      "CWE-306"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-10-08T22:01:29Z",
    "nvd_published_at": null,
    "severity": "HIGH"
  },
  "details": "## Summary\n\nThe AgentOS server in the `praisonai` TypeScript/npm package ships an insecure default: it binds `0.0.0.0`, sets no API key, and uses CORS `*` with credentials. The API-key middleware is only registered when an API key is configured, so the documented quickstart (`new AgentOS({agents:[...]}).serve({port})`) exposes, **unauthenticated**, `GET /api/agents` (which leaks agent names/roles/instructions, i.e. system prompts) and `POST /api/chat` (which invokes agents). Any network peer can read agent system prompts and drive the agent. Runtime-confirmed; severity High.\n\n## Details\n\n### Affected component\n- Package: `praisonai` (npm / TypeScript). Files `src/praisonai-ts/src/os/config.ts` and `src/praisonai-ts/src/os/agentos.ts` (`AgentOS`).\n\n### Vulnerable code / root cause\n\nPath:\n`src/praisonai-ts/src/os/config.ts`\n\nClass/const:\n`DEFAULT_AGENTOS_CONFIG` / `mergeConfig`\n\nSnippet:\n```ts\nexport const DEFAULT_AGENTOS_CONFIG = {\n  host: \u00270.0.0.0\u0027,\n  corsOrigins: [\u0027*\u0027],\n  apiKey: \u0027\u0027,\n  // ...\n};\n// mergeConfig: apiKey = userConfig?.apiKey ?? process.env.PRAISONAI_AGENTOS_API_KEY ?? \u0027\u0027;\n```\nIssue: defaults bind all interfaces, with an empty API key and wildcard CORS. `apiKey` stays empty unless the developer explicitly sets it.\n\nPath:\n`src/praisonai-ts/src/os/agentos.ts`\n\nFunction:\n`serve` / `_registerRoutes` (Express app)\n\nSnippet:\n```ts\nif (this.config.apiKey) {              // auth middleware ONLY added when apiKey is set\n  app.use((req,res,next) =\u003e { /* 401 unless Bearer/x-auth-token matches */ });\n}\n// routes:\napp.get(`${apiPrefix}/agents`, ...)    // returns name/role/instructions\napp.post(`${apiPrefix}/chat`,  ...)    // calls agent.chat(message)\n```\nIssue: the only auth gate is conditional on a non-empty `apiKey`. With the default empty key, no auth middleware is registered, and `GET /api/agents` (system-prompt disclosure) and `POST /api/chat` (agent invocation) are served to any network client. CORS sets `Access-Control-Allow-Credentials: true` with a wildcard origin.\n\n### Attack flow\n1. Developer deploys AgentOS via the quickstart without setting `apiKey`/`PRAISONAI_AGENTOS_API_KEY`.\n2. Any network peer calls `GET /api/agents` \u2192 receives agent instructions/system prompts.\n3. Any network peer calls `POST /api/chat` \u2192 invokes the agent.\n\n### Why existing protection is bypassed\nThere is no protection in the default config \u2014 the auth gate is skipped when `apiKey` is empty (the default), and the server binds all interfaces.\n\n### Security boundary\nUnauthenticated network access to agent metadata + invocation. This is the CVE-2026-44338 anti-pattern recurring in the TS package, and worse (0.0.0.0 is the default).\n\n## Proof of Concept\n\n### Environment\nReal AgentOS from `src/praisonai-ts` run via ts-node in a node container with default config (stub agent, no LLM needed). `127.0.0.1:18000`. Runnable assets: `PraisonAI-Runtime-Repro\\runtime-files\\` (`docker-compose.agentos.yml`).\n\n### Steps to reproduce\n1. `PRAI-01-01-AgentOS-Agents-NoAuth`: `GET /api/agents` (no Authorization) \u2192 `127.0.0.1:18000`.\n2. `PRAI-01-02-AgentOS-Chat-NoAuth`: `POST /api/chat {\"message\":\"hello from attacker\"}` (no Authorization).\n\n### Expected result\nNon-loopback exposure should require authentication; agent instructions should not be disclosed unauthenticated.\n\n### Actual result\n- `GET /api/agents` \u2192 `200`, leaks `\"instructions\":\"SYSTEM PROMPT SECRET ... PRAISONAI_INTERNAL_SECRET_CANARY_7f3a91\"`; response header `Access-Control-Allow-Credentials: true`.\n- `POST /api/chat` \u2192 `200`, agent invoked (`\"response\":\"...PRAISONAI_AGENTOS_CANARY_7f3a91...\"`).\n\n### Screenshots\n\n**Unauthenticated `/api/agents` leaks agent instructions**\n\nA GET request to `/api/agents` succeeds without an `Authorization` header. The response exposes agent metadata and instructions, including the canary system-prompt value.\n\n\u003cimg width=\"1535\" height=\"829\" alt=\"01-AgentOS-Agents-NoAuth\" src=\"https://github.com/user-attachments/assets/705087e1-8017-46f6-9a91-edb8312e2f26\" /\u003e\n\n**Unauthenticated `/api/chat` invokes the agent**\n\nA POST request to `/api/chat` succeeds without an `Authorization` header. The response confirms that the attacker-controlled message was processed by the configured agent.\n\n\u003cimg width=\"1537\" height=\"833\" alt=\"02-AgentOS-Chat-NoAuth\" src=\"https://github.com/user-attachments/assets/5cdf8f56-b8d8-498b-87bd-44834f39998c\" /\u003e\n\n### Reproduction assets\n\nThe attached archive contains the local Docker runtime used to reproduce the issue with controlled canary values only. It does not contain real secrets, third-party API keys, or production credentials.\n\n[PraisonAI-Runtime-Repro.zip](https://github.com/user-attachments/files/29143421/PraisonAI-Runtime-Repro.zip)\n\n## Impact\nUnauthenticated disclosure of agent configuration/system prompts; unauthenticated agent invocation; LLM cost abuse; possible tool abuse depending on the configured agent\u0027s tools; permissive CORS-with-credentials.\n\n## Suggested remediation\n- Default `host` to `127.0.0.1`; require `apiKey` (fail closed) when binding non-loopback.\n- Do not default `corsOrigins` to `[\u0027*\u0027]`, especially with `Access-Control-Allow-Credentials: true`.\n- Do not return full `instructions` on an unauthenticated endpoint.",
  "id": "GHSA-6wjp-v33h-5cvq",
  "modified": "2026-10-08T22:01:29Z",
  "published": "2026-10-08T22:01:29Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6wjp-v33h-5cvq"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-61426"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/MervinPraison/PraisonAI"
    },
    {
      "type": "WEB",
      "url": "https://www.vulncheck.com/advisories/praisonai-before-unauthenticated-agent-access-via-insecure-defaults"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:L",
      "type": "CVSS_V3"
    }
  ],
  "summary": "PraisonAI: AgentOS defaults to network-exposed no-auth mode, allowing unauthenticated agent invocation and instruction disclosure"
}

CVE-2026-61426 (GCVE-0-2026-61426)

Vulnerability from cvelistv5 – Published: 2026-07-11 13:01 – Updated: 2026-07-13 15:05

Title

PraisonAI before 1.7.3 Unauthenticated Agent Access via Insecure Defaults

Summary

PraisonAI before 1.7.3 contains an insecure default configuration that binds to all interfaces with no API key requirement and wildcard CORS. Unauthenticated attackers can call GET /api/agents to read agent instructions and system prompts, or POST /api/chat to invoke agents without authentication.

Severity

8.8 (High)


                        
                          CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:L/SC:N/SI:N/SA:N

8.6 (High)


                        
                          CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:L

SSVC

Exploitation: poc Automatable: yes Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-07-13 15:04 UTC

CWE

CWE-200 - Exposure of Sensitive Information to an Unauthorized Actor

Assigner

VulnCheck CNA under the mitre root

CNA scorecard B 84/100 over 5953 records in the last 180 days details

References

2 references

URL	Tags
https://github.com/MervinPraison/PraisonAI/securi…	vendor-advisory
https://www.vulncheck.com/advisories/praisonai-be…	third-party-advisory

Impacted products

1 product

Vendor	Product	Version
MervinPraison	PraisonAI	Affected: 0 , < 1.7.3 (semver) Unaffected: 1.7.3 (semver) cpe:2.3:a:praison:praisonai::::::::

Date Public

2026-06-25 00:00

Credits

dinhvaren

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-61426",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-07-13T15:04:48.407773Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-07-13T15:05:01.782Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6wjp-v33h-5cvq"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:npm/praisonai",
          "product": "PraisonAI",
          "vendor": "MervinPraison",
          "versions": [
            {
              "lessThan": "1.7.3",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            },
            {
              "status": "unaffected",
              "version": "1.7.3",
              "versionType": "semver"
            }
          ]
        }
      ],
      "cpeApplicability": [
        {
          "nodes": [
            {
              "cpeMatch": [
                {
                  "criteria": "cpe:2.3:a:praison:praisonai:*:*:*:*:*:*:*:*",
                  "versionEndExcluding": "1.7.3",
                  "vulnerable": true
                }
              ],
              "negate": false,
              "operator": "OR"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "reporter",
          "value": "dinhvaren"
        }
      ],
      "datePublic": "2026-06-25T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "PraisonAI before 1.7.3 contains an insecure default configuration that binds to all interfaces with no API key requirement and wildcard CORS. Unauthenticated attackers can call GET /api/agents to read agent instructions and system prompts, or POST /api/chat to invoke agents without authentication."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 8.8,
            "baseSeverity": "HIGH",
            "privilegesRequired": "NONE",
            "subAvailabilityImpact": "NONE",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "NONE",
            "userInteraction": "NONE",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:L/VA:L/SC:N/SI:N/SA:N",
            "version": "4.0",
            "vulnAvailabilityImpact": "LOW",
            "vulnConfidentialityImpact": "HIGH",
            "vulnIntegrityImpact": "LOW"
          },
          "format": "CVSS"
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "LOW",
            "baseScore": 8.6,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "LOW",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:L",
            "version": "3.1"
          },
          "format": "CVSS"
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-200",
              "description": "Exposure of Sensitive Information to an Unauthorized Actor",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-07-11T13:01:01.057Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "GitHub Security Advisory (GHSA-6wjp-v33h-5cvq)",
          "tags": [
            "vendor-advisory"
          ],
          "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-6wjp-v33h-5cvq"
        },
        {
          "name": "VulnCheck Advisory: PraisonAI before 1.7.3 Unauthenticated Agent Access via Insecure Defaults",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/praisonai-before-unauthenticated-agent-access-via-insecure-defaults"
        }
      ],
      "title": "PraisonAI before 1.7.3 Unauthenticated Agent Access via Insecure Defaults",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-61426",
    "datePublished": "2026-07-11T13:01:01.057Z",
    "dateReserved": "2026-07-09T14:05:21.470Z",
    "dateUpdated": "2026-07-13T15:05:01.782Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted

GHSA-6WJP-V33H-5CVQ

Summary

Details

Affected component

Vulnerable code / root cause

Attack flow

Why existing protection is bypassed

Security boundary

Proof of Concept

Environment

Steps to reproduce

Expected result

Actual result

Screenshots

Reproduction assets

Impact

Suggested remediation

CVE-2026-61426 (GCVE-0-2026-61426)

Tags

Sightings

Nomenclature

Related by attack behaviour