NetSight
medium6.1No CVE yet

GHSA-r3xw-gcpr-rf26

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

Impact

### Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-29r9-67vg-qj56. This link is maintained to preserve external references. ### Original Description PraisonAI before 1.6.78 caches tool approval decisions by tool name only, allowing attackers to reuse initial approvals for subsequent calls with arbitrary arguments. 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.

An attacker can exploit this with local access to the system, without logging in, but a user has to do something, such as open a file or a link. If it succeeds: high risk of data or systems being changed, low risk of outages.

Affected packages

EcosystemPackageAffectedFixed in
pippraisonaiagents<= 1.6.77none recorded

Weakness classification

References