CVE Feed

    Dashboard / CVE / CVE-2026-61447

    CVE-2026-61447

    PraisonAI before 1.6.78 contains a remote code execution vulnerability in CodeAgent._execute_python() that executes LLM-generated Python code without AST validation, import restrictions, or sandbox enforcement. Attackers can influence LLM output through prompt injection to exfiltrate all environment secrets and execute arbitrary code on the host system.

    Published:Jul 11, 2026
    Last Modified:Jul 13, 2026
    EPS:Jul 11, 2026
    EPSS Score:0.00544
    CVSS Score:10

    Affected Products

    Vendor
    Praison
    Product
    Praisonai

    Exploits

    https://www.exploit-db.com/exploits/52639

    Related CVEs

    CVE-2026-61446 (CVSS 8.6) — PraisonAI (praisonaiagents) before 1.6.78 contains a remote code execution vulnerability in the plugin manager…
    CVE-2026-61443 (CVSS 8.6) — PraisonAI before 1.6.78 contains a remote code execution vulnerability in SkillTools.run_skill_script() that e…
    CVE-2026-61440 (CVSS 7.1) — PraisonAI Platform before 0.1.9 fails to properly authorize label and issue-label mutations, allowing workspac…
    CVE-2026-61438 (CVSS 7) — PraisonAI before 4.6.78 contains a remote code execution vulnerability in JobWorkflowExecutor._exec_inline_pyt…
    CVE-2026-61436 (CVSS 8.8) — PraisonAI before 4.6.78 fails to verify Svix webhook signatures in AgentMail webhook mode, allowing unauthenti…
    CVE-2026-61435 (CVSS 8.8) — PraisonAI before 4.6.78 contains an authentication bypass in the Call API agent invocation endpoints (src/prai…
    CVE-2026-61433 (CVSS 8.5) — PraisonAI before 4.6.78 fails to safely encode deployment configuration values when generating Python source c…
    CVE-2026-61430 (CVSS 8.4) — PraisonAI before 1.6.78 contains a server-side request forgery vulnerability in the web_crawl tool that valida…
    CVE-2026-61427 (CVSS 6.9) — PraisonAI before 4.6.78 exposes the MCP HTTP-stream transport without authentication by default: the CLI --api…
    CVE-2026-60087 (CVSS 6.9) — PraisonAI before 1.6.78 caches tool approval decisions by tool name only, allowing attackers to reuse initial …

    Common Vulnerability Scoring System

    Attack Vector
    Network
    Adjacent
    Local
    Physical
    Privileges Required
    None
    Low
    High
    User Interaction
    None
    Required
    Scope
    Unchanged
    Changed
    Confidentiality
    None
    Low
    High
    Integrity
    None
    Low
    High
    Availability
    None
    Low
    High