close
Warn
Audited by Snyk on Aug 4, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). Source SKILL.md defines a session-closing workflow that reviews the full conversation context from the agent’s ongoing chat (user-authored text is ingested as “conversation”), then writes summaries/memory locally.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata