PraisonAI Vulnerabilities

pipAI Agents

AI Threat Alert tracks 196 known vulnerabilities in PraisonAI, 52 rated critical — an AI/ML ai agents in the pip ecosystem. Each CVE includes CVSS severity, EPSS exploit probability, patch status, and CISO-grade analysis.

196
Total CVEs
52
Critical
pip
Ecosystem
Oct 23, 2026
Last CVE
61%
Patch Rate
23d
Avg Time to Patch

Known Vulnerabilities(196 total, page 1 of 8)

SeverityCVE IDSummaryCVSSPublished
HIGHCVE-2026-57146PraisonAI: unauthenticated A2U event streaming exposed7.5Oct 23, 2026HIGHCVE-2026-57144PraisonAI: sandbox fails open, bypassing FS/network limits8.8Oct 23, 2026HIGHCVE-2026-57142PraisonAI: recipe policy bypass self-approves shell tool7.8Oct 23, 2026HIGHCVE-2026-57121PraisonAI: missing ownership check lets members delete data8.1Oct 23, 2026HIGHCVE-2026-57117PraisonAI: shell injection in agent file tools allows RCE8.8Oct 23, 2026CRITICALCVE-2026-57116PraisonAI: unauthenticated AgentOS chat API drives agents9.8Oct 23, 2026HIGHCVE-2026-57114PraisonAI: SSRF via webhook DNS rebinding bypass7.2Oct 23, 2026HIGHCVE-2026-57113PraisonAI: path traversal in template cache deletes dirs8.1Oct 23, 2026HIGHCVE-2026-56840PraisonAI: stored XSS in approval dashboard forces tool approval8.8Oct 23, 2026HIGHCVE-2026-56836PraisonAI: unauthenticated recipe server exposes admin8.2Oct 23, 2026HIGHCVE-2026-56837PraisonAI: missing webhook auth lets forged Linear events drive agent8.6Oct 23, 2026HIGHCVE-2026-56838PraisonAI: recipe run_stream skips dangerous-tool policy7.8Oct 23, 2026HIGHCVE-2026-56834PraisonAI: path traversal in artifact tools leaks files7.5Oct 23, 2026HIGHCVE-2026-56833PraisonAI: path traversal exposes agent logs/history7.5Oct 23, 2026HIGHCVE-2026-56832PraisonAI: Discord approval bypass allows tool call hijack8.8Oct 23, 2026HIGHCVE-2026-56835PraisonAI: Slack app_mention bypasses access policy8.3Oct 23, 2026HIGHCVE-2026-57143PraisonAI: SSRF via LLM-controlled SearxNG URL8.8Oct 12, 2026CRITICALCVE-2026-57118PraisonAI agents: unauthenticated access to agent endpoints9.8Oct 12, 2026CRITICALCVE-2026-62176PraisonAI: code injection in deploy API enables RCE9.1Oct 7, 2026MEDIUMCVE-2026-62179PraisonAI Platform: authz flaw lets members delete issue links6.5Oct 7, 2026CRITICALCVE-2026-57148PraisonAI: hardcoded JWT secret enables auth bypass9.8Sep 15, 2026CRITICALCVE-2026-57147PraisonAI: hardcoded JWT secret allows auth bypass9.8Sep 15, 2026CRITICALCVE-2026-57141PraisonAI: codeMode sandbox escape allows unauthenticated RCE9.8Sep 15, 2026CRITICALCVE-2026-57140PraisonAI: unauthenticated AgentOS API exposes agents9.4Sep 15, 2026CRITICALCVE-2026-57139PraisonAI: unauthenticated MCP server exposes agent tools9.8Sep 15, 2026

Showing 1–25 of 196

Frequently asked questions

What is PraisonAI?

PraisonAI is an AI/ML ai agents tracked by AI Threat Alert for security vulnerabilities in the pip ecosystem.

How many known vulnerabilities does PraisonAI have?

PraisonAI has 196 known CVEs, 52 of them critical, tracked from NVD and GitHub Advisory.

Which ecosystem is PraisonAI distributed in?

PraisonAI is distributed via the pip ecosystem and categorized as ai agents.

Where does the PraisonAI vulnerability data come from?

Vulnerability data is sourced from NVD and GitHub Advisory, enriched with CVSS, EPSS, exploit signals, and patch status for each CVE.

How do I assess the risk of PraisonAI?

Review each CVE below — every entry shows CVSS severity, EPSS exploit probability, exploitation signals, and whether a patched version is available.

Monitor PraisonAI in your stack

Get instant alerts when new vulnerabilities affect PraisonAI. CISO analysis, ATLAS technique mappings, and compliance reports included.

Start Monitoring