CVE-2026-56074 PraisonAI - Tool Approval Cache Bypass via Coarse-Grained Caching
Attackers bypass tool approval prompts in PraisonAI by exploiting coarse-grained caching, enabling silent execution of malicious commands to steal credentials.
- 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-2026-56074?
CVE-2026-56074 is a medium-severity vulnerability in PraisonAI, published on 18 Jun 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 1.5.128 caches tool approval decisions by tool name only, not by invocation arguments, allowing subsequent execute_command calls to bypass approval prompts. Attackers can exploit this by obtaining initial approval for a benign command, then silently exfiltrate API keys and credentials via subsequent shell commands without user consent.
Weakness: CWE-863
Which versions are affected by CVE-2026-56074?
3 open source packages ship an affected version, including praisonaiagents.
| Package | Affected | Fixed in |
|---|---|---|
praisonaiagents PyPI | All versions | 4.5.128 |
praisonaiagents PyPI | All versions | 4.5.128 |
praisonaiagents PyPI | All versions | 4.5.128 |
How do I fix CVE-2026-56074?
Upgrade praisonaiagents to 4.5.128 or later.
Is CVE-2026-56074 being exploited?
It is not confirmed as exploited in the wild, but public exploit code for CVE-2026-56074 exists.
Sources
Also known as GHSA-ffp3-3562-8cv3, PYSEC-2026-2946.