audit-security

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (see SKILL.md Section 4 "Interactive Demo Security" and the Verification steps) instructs the auditor to fetch and inspect external webhook responses, DevTools network headers, and public site endpoints (e.g., webhook responses, https://[domain]/.env and securityheaders.com), meaning the agent will read and interpret untrusted third‑party content as part of its decision-making, which could carry instructions that influence the audit.