legal-writer
Warn
Audited by Snyk on Mar 3, 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's Phase 2 "Legal Research" (SKILL.md) explicitly instructs the agent to call scripts/courtlistener.py and scripts/ecfr_lookup.py to fetch case law and regulatory text from public CourtListener/eCFR/Federal Register APIs and to save/extract holdings for use in drafting, so the agent ingests and acts on open third‑party web content as part of its workflow.
Audit Metadata