CVE-2026-40088
Prior to 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell…
Does this matter?
High impact if exploited, but EPSS currently rates exploitation as unlikely (0.42%). 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 4.5.121, the execute_command function and workflow shell execution are exposed to user-controlled input via agent workflows, YAML definitions, and LLM-generated tool calls, allowing attackers to inject arbitrary shell commands through shell metacharacters. This vulnerability is fixed in 4.5.121.
- CVSS 3.1
- 9.6 CRITICALCVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H
- EPSS
- 0.42% probability · 35th percentile
- CISA KEV
- Not listed
- Weakness
- CWE-78
- Affected
- praison/praisonai
- Source
- security-advisories@github.com
References
- https://github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121Release Notes
- https://github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c79mExploit, Vendor Advisory
Source: NVD record, EPSS from FIRST.org, KEV from CISA. Refreshed daily.