deep-research
Warn
Audited by Snyk on Jun 14, 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 systematic literature search (bibliography_agent) that fetches and ingests outsider-authored web/public academic content (e.g., articles/pages from external databases/URLs) into the agent’s LLM context as readable text for screening and annotation.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata