CVE-2026-57137
PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executabl…
PraisonAI is a multi-agent teams system. From 1.4.0 until 1.7.2, createAgentLoop() in src/praisonai-ts/src/ai/agent-loop.ts passes executable tools to generateText() before invoking the onToolCall approval callback. Because the wrapped AI SDK executes tool handlers during generation, a callback that returns false records tool_rejected only after the denied tool has already produced side effects and populated toolResults. Applications using onToolCall as a human or policy approval boundary can therefore execute rejected file, command, API, or data-modifying operations. This issue is fixed in version 1.7.2.
Why it matters
- ▸ Remotely exploitable over the network — no physical or local access required
- ▸ Low attack complexity — no special conditions needed to exploit
- ▸ Requires low-privilege access first
- ▸ No user interaction needed — can be exploited automatically
Apply the vendor patch as soon as it's available or already released. Review and restrict accounts with the privilege level this vulnerability requires.
This analysis is generated from structured CVSS vector data, CISA KEV cross-referencing, and vendor/product category rules — not a manual expert review. Treat it as a starting point, not a substitute for your own assessment.
CVSS Vector Breakdown
Stay Updated
New CVEs and vulnerability advisories are added continuously as they're disclosed. Subscribe via RSS to get every update the moment it's published — no email or account required.
Subscribe via RSS