Critical severity9.6NVD Advisory· Published Apr 9, 2026· Updated Jun 17, 2026
CVE-2026-40088
CVE-2026-40088
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.
AI Insight
LLM-synthesized narrative grounded in this CVE's description and references.
Affected products
2Patches
Vulnerability mechanics
References
6- github.com/MervinPraison/PraisonAI/security/advisories/GHSA-2763-cj5r-c79mnvdExploitVendor Advisory
- github.com/advisories/GHSA-2763-cj5r-c79mghsaADVISORY
- github.com/MervinPraison/PraisonAI/releases/tag/v4.5.121nvdRelease Notes
- github.com/pypa/advisory-database/tree/main/vulns/praisonai/PYSEC-2026-461.yamlghsa
- nvd.nist.gov/vuln/detail/CVE-2026-40088ghsa
- pypi.org/project/praisonaighsa
News mentions
0No linked articles in our index yet.