UTC

praisonaiagents

50 published advisories; version 4.5.128 or later fixes all of them.

Registry
PyPI
Advisories
50
Latest fix
4.5.128
Exploited in the wild
None listed

Check your projects

shieldpi agent-config checks agent and MCP packages from npm and PyPI, not praisonaiagents. Any scanner that reads the OSV database finds it in your lockfiles, for example Google's open-source OSV-Scanner.

osv-scanner scan source -r .

Or check a lockfile against ShieldMap in your browser.

Provenance

Source: github.com/mervinpraison/praisonai, named in the package metadata (not verified)

0 of the last 10 releases of praisonaiagents were published with build provenance: a signed record of the repository and commit each was built from, which the registry checks before it accepts the release.

  • 1.7.24
  • 1.7.23
  • 1.7.22
  • 1.7.21
  • 1.7.20
  • 1.7.19
  • 1.7.18
  • 1.7.17
  • 1.7.16
  • 1.7.15

Green: published with provenance. Grey: without.

OpenSSF Scorecard has not scored this repository.

Provenance from deps.dev (CC BY 4.0); Scorecard from OpenSSF (CDLA-Permissive-2.0). As of 2026-11-18.

Advisories
AdvisorySeverityAffectedFixed inPublished
PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary argumentsCVE-2026-60087Medium<= 1.6.771.6.782026-10-08
PraisonAI: CodeAgent Executes LLM-Generated Code Without Sandboxing and Leaks All Environment SecretsCVE-2026-61447Critical<= 1.6.771.6.782026-10-08
PraisonAI: Unsafe Dynamic Module Loading Leads to Arbitrary Code Execution via tools.py in AgentFlowCVE-2026-61437High<= 1.6.771.6.782026-10-08
PraisonAI: FastContext path resolution permits absolute and traversal reads outside the workspaceCVE-2026-61432Medium<= 1.6.771.6.782026-10-08
PraisonAI: SkillTools Executes Scripts Without Path Containment ValidationCVE-2026-61443High<= 1.6.771.6.782026-10-08
PraisonAI: Plugin Auto-Discovery Executes Arbitrary Python Files Without VerificationCVE-2026-61446High<= 1.6.771.6.782026-10-08
PraisonAI: DNS rebinding bypass in `web_crawl` SSRF protection allows internal response disclosureCVE-2026-61430High<= 1.6.771.6.782026-10-08
PraisonAI: Project config can auto-save agent output outside the project rootCVE-2026-60089Medium<= 1.6.771.6.782026-10-08
PraisonAI: Crawl4AI/Chromium backend is also affected by the `web_crawl` SSRF validation bypassCVE-2026-61429High<= 1.6.771.6.782026-10-07
praisonaiagents web_crawl vulnerable to SSRF via redirect-followingCVE-2026-55525High< 1.6.581.6.582026-08-25
praisonaiagents: AgentServer declares auth_token but never enforces it on any routeCVE-2026-55528High< 1.6.581.6.582026-08-25
praisonaiagents has a `web_crawl` SSRF protection bypass via unchecked redirect targetsCVE-2026-55523High>= 1.5.128, < 1.6.581.6.582026-08-25
praisonaiagents: ast_grep_rewrite rewrites arbitrary files without the @require_approval gate enforced on every sibling mutation toolCVE-2026-55530Medium< 1.6.581.6.582026-08-25
praisonaiagents vulnerable to arbitrary file write via unsanitized `user_id` in `FileMemory.__init__()` — path traversal to any writable locCVE-2026-55527High< 1.6.581.6.582026-08-25
PraisonAI workflow include bypasses tools.py autoload opt-in and executes included recipe codeCVE-2026-55522High>= 0.12.12, < 1.6.581.6.582026-08-25
praisonaiagents vulnerable to SSRF in web_crawl tool via redirect-following and DNS rebinding (validate-then-fetch gap)CVE-2026-55524High< 1.6.581.6.582026-08-25
praisonaiagents has an SSRF protection bypass in `spider_tools._host_is_blocked()` via DNS-resolved hostnames (`127.0.0.1.nip.io`)CVE-2026-55526High< 1.6.581.6.582026-08-25
PraisonAI: Arbitrary File Read via `@file:` Mention Path TraversalCVE-2026-57129High<= 1.6.481.6.592026-06-18
PraisonAI: Unauthenticated Event Injection via SSE `/publish` EndpointCVE-2026-57128Medium<= 1.6.481.6.592026-06-18
PraisonAI: Unauthenticated RCE via Jobs API + Approval BypassCVE-2026-57125Critical< 1.6.591.6.592026-06-18
PraisonAI: Server-Side Request Forgery (SSRF) in SearxNG / search_web tools via attacker-controlled searxng_url parameterCVE-2026-57143High< 1.6.611.6.612026-06-18
PraisonAI: SpiderTools redirect-target SSRF protection bypassCVE-2026-57115Medium<= 1.6.581.6.592026-06-18
PraisonAI: IMAP Command Injection via Unsanitized Email Search ParametersCVE-2026-57130High<= 1.6.481.6.592026-06-18
PraisonAI: execute_code sandbox bypass: str.format C-level attribute access reads every blocklisted dunderCVE-2026-57120Medium< 1.6.591.6.592026-06-18
PraisonAI ToolsMCPServer legacy SSE transport accepts attacker Host/Origin and exposes registered toolsCVE-2026-57112High>= 0.6.0, <= 1.6.581.6.592026-06-18
praisonaiagents: SSRF guard validates literal IPs only and never resolves DNSCVE-2026-57126High<= 1.6.481.6.592026-06-18
PraisonAI: MCP SSE transport binds 0.0.0.0 with no authentication and no Origin validation; bundled SecurityConfig is never wired inCVE-2026-57123Critical< 1.6.591.6.592026-06-18
PraisonAI AgentTeam.launch exposes unauthenticated remote agent listing and invocation endpointsCVE-2026-57118Critical< 1.6.591.6.592026-06-18
PraisonAI vulnerable to sandbox escape via `print.__self__` builtins module leak in `execute_code` (subprocess mode)CVE-2026-47392Critical<= 1.6.391.6.402026-05-29
PraisonAI spider_tools SSRF protection bypass via alternate loopback host encodingsCVE-2026-47390Medium<= 1.6.391.6.402026-05-29
PraisonAI CLI automatically resolves @url mentions in prompt text and can read loopback URLs into model contextCVE-2026-47395Medium<= 1.6.391.6.402026-05-29
PraisonAI has unsafe tool resolution in `ToolExecutionMixin.execute_tool`: undeclared `__main__` callables executeCVE-2026-44339High<= 1.6.361.6.372026-05-11
PraisonAI has an SSRF bypassCVE-2026-44335High<= 1.6.311.6.322026-05-06
PraisonAI: SQL Injection via unvalidated `table_prefix` in 9 conversation store backends (incomplete fix for CVE-2026-40315)CVE-2026-41496High<= 1.6.71.6.82026-04-17
PraisonAIAgents: Path Traversal via Unvalidated Glob Pattern in list_files Bypasses Workspace BoundaryCVE-2026-40152Medium< 1.5.1281.5.1282026-04-10
PraisonAIAgents has SSRF and Local File Read via Unvalidated URLs in web_crawl ToolCVE-2026-40150High< 1.5.1281.5.1282026-04-10
PraisonAI Browser Server allows unauthenticated WebSocket clients to hijack connected extension sessionsCVE-2026-40289Critical<= 1.5.1391.5.1402026-04-10
PraisonAI: Coarse-Grained Tool Approval Cache Bypasses Per-Invocation Consent for Shell CommandsCVE-2026-56074Medium< 4.5.1284.5.1282026-04-10
PraisonAI Vulnerable to RCE via Automatic tools.py ImportCVE-2026-40287High<= 1.5.1391.5.1402026-04-10
PraisonAIAgents: Arbitrary File Read via read_skill_file Missing Workspace Boundary and Approval GateCVE-2026-40117Medium< 1.5.1281.5.1282026-04-10
PraisonAIAgents: SSRF via unvalidated URL in `web_crawl` httpx fallbackCVE-2026-40160High>= 0.13.23, < 1.5.1281.5.1282026-04-10
PraisonAIAgents has an OS Command Injection via shell=True in Memory Hooks Executor (memory/hooks.py)CVE-2026-40111Critical<= 1.5.1261.5.1282026-04-10
PraisonAIAgents: Environment Variable Secret Exfiltration via os.path.expandvars() Bypassing shell=False in Shell ToolCVE-2026-40153High< 1.5.1281.5.1282026-04-10
PraisonAI has critical RCE via `type: job` workflow YAMLCVE-2026-40288Critical<= 1.5.1391.5.1402026-04-10
PraisonAI: Cross-Origin Agent Execution via Hardcoded Wildcard CORS and Missing Authentication on AGUI EndpointGHSA-x462-jjpc-q4q4High< 4.5.1284.5.1282026-04-10
PraisonAI has Memory State Leakage and Path Traversal in MultiAgent Context HandlingCVE-2026-56078Medium<= 1.5.1141.5.1152026-04-08
PraisonAI has sandbox escape via exception frame traversal in `execute_code` (subprocess mode)CVE-2026-39888Critical<= 1.5.1141.5.1152026-04-08
PraisonAI Has SSRF in FileTools.download_file() via Unvalidated URLCVE-2026-34954High<= 1.5.941.5.952026-04-01
PraisonAI: Python Sandbox Escape via str Subclass startswith() Override in execute_codeCVE-2026-34938Critical<= 1.5.891.5.902026-04-01
PraisonAI: Shell Injection in run_python() via Unescaped $() SubstitutionCVE-2026-34937High<= 1.5.891.5.902026-04-01

Sources: GitHub Advisory Database, reviewed and malware advisories (CC BY 4.0, https://github.com/advisories); advisories published by Cursor (https://github.com/cursor/cursor/security/advisories); advisories published by OpenClaw (https://github.com/openclaw/openclaw/security/advisories); advisories published by vLLM (https://github.com/vllm-project/vllm/security/advisories); advisories published by Open WebUI (https://github.com/open-webui/open-webui/security/advisories); advisories published by n8n (https://github.com/n8n-io/n8n/security/advisories); advisories published by Flowise (https://github.com/FlowiseAI/Flowise/security/advisories); advisories published by Langflow (https://github.com/langflow-ai/langflow/security/advisories); advisories published by the MCP Python SDK project (https://github.com/modelcontextprotocol/python-sdk/security/advisories); advisories published by MLflow (https://github.com/mlflow/mlflow/security/advisories); CISA Known Exploited Vulnerabilities catalog (CC0). Data as of 2026-11-22. ShieldMap describes how each problem works and how to fix it; it does not publish exploit code. Report a correction to [email protected].