office-hours
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 YC application pitch and "Garry Tan" personal notes are an openly disclosed promotion for the author's own program, which is not part of the design-doc task, so the most severe content is medium rather than malicious.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow exposes outsider text only through Phase 2.75 landscape research: the agent runs Aside or WebSearch queries, then reads the top 2-3 cited arbitrary web sources, so an outsider must publish content that the agent actively searches for and fetches.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata