accessibility-ux

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows (e.g., "Run automated scans" in references/wcag-audit-patterns.md and its implementation playbook, plus explicit CLI examples like "npx pa11y https://example.com" and instructions in references/skills/fixing-metadata.md to "verify social cards render on a real URL" and use external validators) require fetching and analyzing open/public web pages, which are untrusted third‑party content that the agent must read and act on as part of its workflow.