headroom
Warn
Audited by Snyk on Aug 7, 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 ingests outsider-authored free text whenever the agent passes “tool results / API responses / search hits” into SmartCrusher (scripts/smart_crusher.py) for selection and then sends the compressed content to the LLM.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata