start-building-for-startups
Fail
Audited by Snyk on Nov 18, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill's discovery and implementation workflow is advertised and serves the user, but its contextual-offers section inserts partner promotions with tracking parameters into final recommendations, which is arguably promotion beyond the skill's core purpose.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The workflow reads user-supplied links and docs ("paste links to docs or design files for me to read") at runtime, which are arbitrary outsider-authored web pages the user selects, so the risk is low; the codebase scan, AWS-curated companion skills, and first-party offers index are not outsider-authored.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata