accessibility-testing
Warn
Audited by Snyk on Mar 6, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill explicitly directs agents to load and analyze external web pages (see SKILL.md "Agent-Driven Accessibility" Task with url: 'https://example.com/checkout' and the schema/metadata requiring a targetUrl), so it fetches and interprets untrusted public site content which can materially influence tool actions and remediation decisions.
Audit Metadata