composio
Fail
Audited by Snyk on Nov 16, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The reviewed SKILL.md and reference files are ordinary Composio integration guidance with no malicious intent, but the bundled composio.skill archive is compressed binary that cannot be inspected, so its contents could hide something from the user.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required Email Triage, GitHub PR Monitor, and Multi-App workflows make the agent consume Gmail inbox messages, GitHub PR events, and Slack messages that outsiders can send without the agent selecting them, so the text reaches the LLM as an unsolicited feed.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata