project-state
Warn
Audited by Snyk on Mar 17, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's research phase (research.py and SKILL.md Phase 5) invokes external DOGPILE_SKILL and ARXIV_SKILL subprocesses to fetch web/search/arXiv results and then parses and incorporates those untrusted public outputs into the report and gap_analysis (compute_gaps), so third‑party content can materially influence decisions and actions and thus enable indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata