academic-lectures
Warn
Audited by Snyk on Apr 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to run WebSearch / light PubMed searches and ingest the resulting papers (titles, PMIDs/URLs, relevance notes) into resources/daily-*.md and resources/references.md (see SKILL.md "Light PubMed search" and references/scheduled-prep.md Phase 1/Phase 2 tasks), and these ingested third‑party pages are then read and used to drive outline generation, LQS decisions, image prompts, and slide assembly—so external web content can materially influence agent actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata