employer-footprint

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

• Third-party content exposure detected (high risk: 1.00). The skill (SKILL.md and references/digital-footprint-audit.md) explicitly instructs the agent to perform parallel WebSearch/WebFetch/Task tool calls to fetch and analyse publicly available, user-generated content from Google search results, LinkedIn, Twitter/X, GitHub, news sites, personal websites and other public social media, and to use those findings to score, synthesise, and drive recommendations and follow-up actions—therefore it consumes untrusted third-party content that can materially influence agent decisions.