llm-models
Warn
Audited by Snyk on Aug 6, 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). SKILL.md shows a CLI that runs a specified OpenRouter model with user-provided JSON (the
--inputprompt), so outsider-authored free text is ingested at runtime by the LLM without any intermediary selecting a specific trusted item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata