reflect
Warn
Audited by Snyk on Oct 24, 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). The skill reads conversation transcripts from disk using shell commands (
agent-transcripts/*.jsonl), which contain user-authored messages and interactive session content.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata