ii-commons
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). SKILL.md describes running the upstream CLI to fetch arXiv/PubMed/PMC/policy documents and then retrieve full-document Markdown (e.g., via
markdown), which at runtime would ingest outsider-authored document text into the agent’s LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata