ai-research-explore
Warn
Audited by Snyk on Jul 27, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). The skill’s runtime workflow includes a “free-first” external lookup pass (e.g., URL/arXiv/DOI/GitHub providers) that fetches outsider-authored text from public web APIs/pages and/or readmes, stores it in
sources/records/*, and then downstream LLM passes consume those records (e.g., vialookup_bundle/lookup_recordsembedded into the agent context).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata