lighthouse
Warn
Audited by Snyk on Jun 26, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). The skill ingests outsider-authored free text when it runs Lighthouse against a user-supplied
<url>(or detected dev-server URL) and Lighthouse fetches and parses the target page’s HTML/text into the generatedlighthouse-report.json, which the workflow then reads viajq(i.e., runtime web content → LLM context through the report parsing/output).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata