ingest-compliance-doc
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). This skill explicitly accepts a PDF path or URL (SKILL.md and ingest_compliance.py's ingest(path) argument), runs the extractor on that input and then feeds extracted content into doc2qra and the memory store, so arbitrary third‑party documents fetched via URL are read/interpreted and can materially influence downstream LLM outputs and stored decisions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata