setup-engine
Warn
Audited by Snyk on Jul 10, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Yes—when the skill is in MEDIUM/HIGH risk mode it performs WebSearch/WebFetch and “fetch[es] and extract[s]” breaking/deprecated-changes content from web pages, which becomes readable free text inserted into the agent’s LLM context to generate the reference docs.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata