bug-reporting

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). This skill's guidance explicitly expects agents to ingest and act on results from scans of public URLs (e.g., the "Guidance for Automated Tools and AI Agents" section which shows commands like "npx axe https://example.com/shop", requires preserving HTML snippets and including the Page URL), so it consumes untrusted third‑party web content that can materially influence reporting and follow-up actions.