CVE-2026-39891
When user input from agent.start() is passed directly into these tools without escaping, template expressions in the input are executed rather than treated as literal text.
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.56%). Schedule it in the normal patch cycle and watch for a rise in EPSS or a public exploit.
Description
PraisonAI is a multi-agent teams system. Prior to 4.5.115, the create_agent_centric_tools() function returns tools (like acp_create_file) that process file content using template rendering. When user input from agent.start() is passed directly into these tools without escaping, template expressions in the input are executed rather than treated as literal text. This vulnerability is fixed in 4.5.115.
- CVSS 3.1
- 8.8 HIGHCVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H
- EPSS
- 0.56% probability · 45th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-94
- Affected
- praison/praisonai
- Source
- security-advisories@github.com
References
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hwg5-x759-7wjgExploit, Vendor Advisory
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-hwg5-x759-7wjgExploit, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.