copy-editing
Warn
Audited by Snyk on Aug 26, 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). SKILL.md describes a copy-editing workflow that reads first-party “existing copy” supplied by the user at runtime (e.g., the prompt text in evals/evals.json), so the LLM ingests outsider-authored free text directly for editing.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata