social-engineering-audit

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

• Third-party content exposure detected (high risk: 0.90). The skill's Audit Methodology Step 3 and the "OSINT Exposure" section explicitly require gathering and using publicly available/untrusted content (social media, paste sites/breach databases, public records, code repositories, domain/DNS data) which the agent would read and use to craft pretexts and influence next actions.