extract-design
Warn
Audited by Snyk on Aug 8, 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 workflow ingests user-supplied HTML/CSS content (including a live URL via “fetch with WebFetch or Playwright MCP”) and for HTML/CSS it reads that text through
scripts/extract_primitives.py(e.g.,raw = p.read_text(...)and parses CSS/HTML into JSON), meaning outsider-authored free text can be delivered to the extractor without selecting a specific item.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata