ingest-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). The SKILL.md and ingest_compliance.py explicitly accept a "PDF path or URL" and pass that URL to the extractor/doc2qra/taxonomy pipeline (e.g., extractor run.sh and doc2qra are invoked with the provided path), which means arbitrary public web pages/PDFs can be fetched and their user-generated/untrusted content is read by an LLM and stored in memory—creating a clear avenue for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata