CVE-2026-60087 PraisonAI before 1.6.78 Tool Approval Cache Bypass
Attackers bypass tool approval checks in PraisonAI by reusing cached decisions, enabling unauthorized execution of dangerous file write operations.
- Exploited in the wild
- Not known
- Login needed
- Not needed
- Attackable
- Local or same network only
- Victim action needed
- A user has to click or open something
- Fix
- Available
What is CVE-2026-60087?
CVE-2026-60087 is a medium-severity vulnerability in MervinPraison PraisonAI, published on 15 Jul 2026. It can only be exploited from the same machine or local network, and only if a user opens a file or follows a link.
Official 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.
Weakness: CWE-863
Which versions are affected by CVE-2026-60087?
3 open source packages ship an affected version, including praisonaiagents.
| Package | Affected | Fixed in |
|---|---|---|
praisonaiagents PyPI | All versions | 1.6.78 |
praisonaiagents PyPI | All versions | 1.6.78 |
praisonaiagents PyPI | All versions | 1.6.78 |
How do I fix CVE-2026-60087?
Upgrade praisonaiagents to 1.6.78 or later.
Is CVE-2026-60087 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-60087 exists.
Sources
Also known as CVE-2026-62164, GHSA-29r9-67vg-qj56, PYSEC-2026-4265.