novel-script
Warn
Audited by Snyk on Aug 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). runtime path: the only outsider-authored free text that can enter at runtime is user-provided
script.jsonfields (e.g.,episodes[*].scenes[*].flow[*].action|line|deliveryrendered/validated byscripts/novel-script.mjs, and if attacker supplies those files there is no forced upstream selection before the LLM/logic consumes them), so the workflow exposes untrusted free text.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata