deep-reader
Warn
Audited by Snyk on Jul 27, 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 required workflow ingests the OUTSIDER-authored source document text (e.g., user-provided PDF/EPUB/DOCX/TXT/MD) via
scripts/prepare-text.sh, which converts it intoworkspace/source.txt(prose) that later gets passed into the LLM during the chapter-reading steps.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata