service-area-pages
Fail
Audited by Snyk on Nov 17, 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 purpose is writing honest local service-area pages, and its file writes, API keys and fetches are disclosed in the body, but its metadata declares
writes: []while the body appends to./brand/assets.mdand writes campaign files, which slightly understates its own activity.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The required workflow quotes customer reviews verbatim into every town page's proof section and mines reviews and Google's search questions for FAQ content, so outsiders can post text into a feed the agent reads without the agent selecting a specific item.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata