long-form-writer

Warn

Audited by Snyk on Mar 8, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The skill explicitly ingests user-generated chat history (see SKILL.md "Pattern 3: Chat History to Guide" / --chat-history chat.json) and the runtime script scripts/generate.py (enrich_cases and generate) inserts those third-party chat cases into generated content, so untrusted external text is read and can influence generation decisions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 8, 2026, 02:25 AM