book-distill

Warn

Audited by Snyk on Jul 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.85). SKILL.md describes a runtime flow that reads outsider-authored book content (PDF/EPUB extraction treated as untrusted) and then uses it to write the agent’s own reference files, and those extracted text passages become LLM-readable context during the “Reading a chapter” and distillation steps.

Issues (1)

W011
MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jul 21, 2026, 07:55 PM
Issues
1
Security Audit — snyk — book-distill