find-the-original-image
Warn
Audited by Snyk on Aug 3, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). The skill’s runtime workflow instructs opening and harvesting text from “match pages” found via reverse-image engines (step 8: “Open them… and any surrounding article text”), so outsider-authored HTML on those pages is ingested into the LLM for analysis.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata