THREATOPS
THREAT OPS › Threat News › [GHSA] GHSA-29r9-67vg-qj56 (medium) — PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments

[GHSA] GHSA-29r9-67vg-qj56 (medium) — PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments

medgithub_advisoriesPublished 2026-10-08

GHSA-29r9-67vg-qj56 Severity: medium CVE: CVE-2026-60087

PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments

## Summary

PraisonAI gates dangerous tools (file writes, deletes, shell/code execution) behind an interactive approval prompt. The first approval of a tool is cached for the remainder of the run and silen

Indicators of compromise

Original source: https://github.com/advisories/GHSA-29r9-67vg-qj56