02-platform-audit

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly requires the agent to perform manual reviews of public social media profiles and to use public sources such as Meta Ad Library (adslibrary.facebook.com) and SimilarWeb to collect user-generated/open web content that the agent must read and interpret to produce audits and recommendations, so untrusted third‑party content could materially influence actions.