copywriting
Fail
Audited by Snyk on Nov 12, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The visible skill is a brand-copy workflow whose behavior is disclosed, but the Humanize section points the agent at an unvetted third-party npm package (
npx sshlg-skills humanizers) with no verification, which is a risky but not clearly malicious suggestion.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required copywriting workflow reads the project's own brand pack and bundled references, but the "before a video" research step in research-outliers.md has the agent browse other creators' accounts and read their hooks, which is outsider-authored text it must actively fetch, so this is low.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata