web-scraper
Warn
Audited by Snyk on Jul 9, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.95). Yes—at runtime the skill uses WebFetch/Browser automation to retrieve outsider-authored web page text (e.g., TARGET_URL content) and then feeds that readable page content into the LLM via the WebFetch “prompt” (Phase 2 Step 2.1) and extraction prompts (Phase 3 Strategy A).
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata