setup-engine
Warn
Audited by Snyk on Aug 24, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). In Section 7 (“Populate Engine Reference Docs”), the skill uses WebSearch/WebFetch to find and “fetch and extract” breaking changes/deprecated APIs from official documentation when the engine version is beyond the LLM cutoff, meaning outsider-authored free text can be ingested only insofar as search results/web pages (not an authenticated first-party source) are fetched.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata