Verified

ghsa:GHSA-R3XW-GCPR-RF26: praisonaiagents <= 1.6.77

Duplicate Advisory: PraisonAI: Human-in-the-loop tool approval is cached by tool name and silently reused for all subsequent calls with arbitrary arguments. Affected range: <= 1.6.77.

GHSA-r3xw-gcpr-rf26

Affected technology

praisonaiagents · <= 1.6.77
Vendor not specified by the source

Component: Not specified by the source

Attack conditions (Source advisory, CVSS 3.1): Local · No privileges required · User interaction required

What an attacker can do

Attackers can exploit this by obtaining approval for a benign operation and then executing dangerous file write operations with unreviewed parameters in the same session. Source advisory’s CVSS 3.1 assessment rates confidentiality impact as none; integrity impact as high; availability impact as low.

GHSA-r3xw-gcpr-rf26

Affected technology

praisonaiagents · <= 1.6.77
Vendor not specified by the source

Component: Not specified by the source

Attack conditions (OSV, CVSS 4.0): Local · No privileges required · Passive user interaction

What an attacker can do

Attackers can exploit this by obtaining approval for a benign operation and then executing dangerous file write operations with unreviewed parameters in the same session. OSV’s CVSS 4.0 assessment rates confidentiality impact as none; integrity impact as high; availability impact as low.

Published 13-Oct-2026 07:40 UTC

Product: praisonaiagents
KEV: no

Provenance

GitHub Advisory Database · Source record · observed 2026-10-08 18:27:24.781324+00:00 UTC
OSV.dev · Source record · observed 2026-10-08 18:36:34.954917+00:00 UTC

Stable permalink: https://cybercodered.org/item/adv-ghsa-ghsa-r3xw-gcpr-rf26.html