accessibility-compliance

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly runs accessibility scanners against arbitrary HTTP(S) sites—e.g., scripts/check_accessibility.py invokes "npx axe " and SKILL.md/install.sh/test.sh show running axe/lighthouse on external URLs—so it ingests untrusted public web content (user-provided URLs) that can materially influence findings and follow-up actions.