a11y-ally

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

• Third-party content exposure detected (low risk: 0.10). The required workflow visits and audits arbitrary target URLs provided by the user, ingesting content from web pages into the agent runtime.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill injects axe-core from cdnjs.cloudflare.com at runtime via script injection in browser evaluation, representing a weak/unknown/suspicious external dependency.