Vulnerability-Lookup

CNVD-2026-18145

Vulnerability from cnvd - Published: 2026-04-22

Title

PraisonAI操作系统命令注入漏洞（CNVD-2026-18145）

Description

PraisonAI是一个低代码多智能体协作框架。 PraisonAI存在操作系统命令注入漏洞，该漏洞源于SubprocessSandbox在所有模式下均依赖字符串模式匹配来阻止危险命令，且阻止列表未包含sh或bash独立可执行文件，攻击者可利用该漏洞导致在STRICT模式下轻易逃逸沙箱。

Severity

高

Patch Name

PraisonAI操作系统命令注入漏洞（CNVD-2026-18145）的补丁

Patch Description

PraisonAI是一个低代码多智能体协作框架。 PraisonAI存在操作系统命令注入漏洞，该漏洞源于SubprocessSandbox在所有模式下均依赖字符串模式匹配来阻止危险命令，且阻止列表未包含sh或bash独立可执行文件，攻击者可利用该漏洞导致在STRICT模式下轻易逃逸沙箱。目前，供应商发布了安全公告及相关补丁信息，修复了此漏洞。

Formal description

厂商已发布了漏洞修复程序，请及时关注更新： https://github.com/MervinPraison/PraisonAI/releases

Reference

https://nvd.nist.gov/vuln/detail/CVE-2026-34955

Impacted products

Name
PraisonAI PraisonAI <4.5.97

Show details on source website

JSON

To clipboard

{
  "cves": {
    "cve": {
      "cveNumber": "CVE-2026-34955",
      "cveUrl": "https://nvd.nist.gov/vuln/detail/CVE-2026-34955"
    }
  },
  "description": "PraisonAI\u662f\u4e00\u4e2a\u4f4e\u4ee3\u7801\u591a\u667a\u80fd\u4f53\u534f\u4f5c\u6846\u67b6\u3002\n\nPraisonAI\u5b58\u5728\u64cd\u4f5c\u7cfb\u7edf\u547d\u4ee4\u6ce8\u5165\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8eSubprocessSandbox\u5728\u6240\u6709\u6a21\u5f0f\u4e0b\u5747\u4f9d\u8d56\u5b57\u7b26\u4e32\u6a21\u5f0f\u5339\u914d\u6765\u963b\u6b62\u5371\u9669\u547d\u4ee4\uff0c\u4e14\u963b\u6b62\u5217\u8868\u672a\u5305\u542bsh\u6216bash\u72ec\u7acb\u53ef\u6267\u884c\u6587\u4ef6\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u5bfc\u81f4\u5728STRICT\u6a21\u5f0f\u4e0b\u8f7b\u6613\u9003\u9038\u6c99\u7bb1\u3002",
  "formalWay": "\u5382\u5546\u5df2\u53d1\u5e03\u4e86\u6f0f\u6d1e\u4fee\u590d\u7a0b\u5e8f\uff0c\u8bf7\u53ca\u65f6\u5173\u6ce8\u66f4\u65b0\uff1a\r\nhttps://github.com/MervinPraison/PraisonAI/releases",
  "isEvent": "\u901a\u7528\u8f6f\u786c\u4ef6\u6f0f\u6d1e",
  "number": "CNVD-2026-18145",
  "openTime": "2026-04-22",
  "patchDescription": "PraisonAI\u662f\u4e00\u4e2a\u4f4e\u4ee3\u7801\u591a\u667a\u80fd\u4f53\u534f\u4f5c\u6846\u67b6\u3002\r\n\r\nPraisonAI\u5b58\u5728\u64cd\u4f5c\u7cfb\u7edf\u547d\u4ee4\u6ce8\u5165\u6f0f\u6d1e\uff0c\u8be5\u6f0f\u6d1e\u6e90\u4e8eSubprocessSandbox\u5728\u6240\u6709\u6a21\u5f0f\u4e0b\u5747\u4f9d\u8d56\u5b57\u7b26\u4e32\u6a21\u5f0f\u5339\u914d\u6765\u963b\u6b62\u5371\u9669\u547d\u4ee4\uff0c\u4e14\u963b\u6b62\u5217\u8868\u672a\u5305\u542bsh\u6216bash\u72ec\u7acb\u53ef\u6267\u884c\u6587\u4ef6\uff0c\u653b\u51fb\u8005\u53ef\u5229\u7528\u8be5\u6f0f\u6d1e\u5bfc\u81f4\u5728STRICT\u6a21\u5f0f\u4e0b\u8f7b\u6613\u9003\u9038\u6c99\u7bb1\u3002\u76ee\u524d\uff0c\u4f9b\u5e94\u5546\u53d1\u5e03\u4e86\u5b89\u5168\u516c\u544a\u53ca\u76f8\u5173\u8865\u4e01\u4fe1\u606f\uff0c\u4fee\u590d\u4e86\u6b64\u6f0f\u6d1e\u3002",
  "patchName": "PraisonAI\u64cd\u4f5c\u7cfb\u7edf\u547d\u4ee4\u6ce8\u5165\u6f0f\u6d1e\uff08CNVD-2026-18145\uff09\u7684\u8865\u4e01",
  "products": {
    "product": "PraisonAI PraisonAI \u003c4.5.97"
  },
  "referenceLink": "https://nvd.nist.gov/vuln/detail/CVE-2026-34955",
  "serverity": "\u9ad8",
  "submitTime": "2026-04-20",
  "title": "PraisonAI\u64cd\u4f5c\u7cfb\u7edf\u547d\u4ee4\u6ce8\u5165\u6f0f\u6d1e\uff08CNVD-2026-18145\uff09"
}

CVE-2026-34955 (GCVE-0-2026-34955)

Vulnerability from cvelistv5 – Published: 2026-04-03 23:04 – Updated: 2026-04-06 19:06

Title

PraisonAI: Sandbox Escape via shell=True and Bypassable Blocklist in SubprocessSandbox

Summary

PraisonAI is a multi-agent teams system. Prior to version 4.5.97, SubprocessSandbox in all modes (BASIC, STRICT, NETWORK_ISOLATED) calls subprocess.run() with shell=True and relies solely on string-pattern matching to block dangerous commands. The blocklist does not include sh or bash as standalone executables, allowing trivial sandbox escape in STRICT mode via sh -c '<command>'. This issue has been patched in version 4.5.97.

Severity

8.8 (High)


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

SSVC

Exploitation: poc Automatable: no Technical Impact: total

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-04-06 19:06 UTC

CWE

CWE-78 - Improper Neutralization of Special Elements used in an OS Command ('OS Command Injection')

Assigner

GitHub_M mitre root

References

1 reference

URL	Tags
https://github.com/MervinPraison/PraisonAI/securi…	x_refsource_CONFIRM

Impacted products

1 product

Vendor	Product	Version
MervinPraison	PraisonAI	Affected: < 4.5.97

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-34955",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-04-06T19:06:05.667759Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-04-06T19:06:17.563Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "PraisonAI",
          "vendor": "MervinPraison",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 4.5.97"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "PraisonAI is a multi-agent teams system. Prior to version 4.5.97, SubprocessSandbox in all modes (BASIC, STRICT, NETWORK_ISOLATED) calls subprocess.run() with shell=True and relies solely on string-pattern matching to block dangerous commands. The blocklist does not include sh or bash as standalone executables, allowing trivial sandbox escape in STRICT mode via sh -c \u0027\u003ccommand\u003e\u0027. This issue has been patched in version 4.5.97."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "LOCAL",
            "availabilityImpact": "HIGH",
            "baseScore": 8.8,
            "baseSeverity": "HIGH",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "HIGH",
            "privilegesRequired": "LOW",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:H/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-78",
              "description": "CWE-78: Improper Neutralization of Special Elements used in an OS Command (\u0027OS Command Injection\u0027)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-04-03T23:04:25.792Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-r4f2-3m54-pp7q",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-r4f2-3m54-pp7q"
        }
      ],
      "source": {
        "advisory": "GHSA-r4f2-3m54-pp7q",
        "discovery": "UNKNOWN"
      },
      "title": "PraisonAI: Sandbox Escape via shell=True and Bypassable Blocklist in SubprocessSandbox"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-34955",
    "datePublished": "2026-04-03T23:04:25.792Z",
    "dateReserved": "2026-03-31T17:27:08.662Z",
    "dateUpdated": "2026-04-06T19:06:17.563Z",
    "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.

Detection rules are retrieved from Rulezet.

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

CNVD-2026-18145

CVE-2026-34955 (GCVE-0-2026-34955)

Tags

Sightings

Nomenclature

Related by attack behaviour