job-search-strategist

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly instructs the agent to use web search and web_fetch to gather and interpret open/public third-party content—naming Glassdoor/Indeed reviews, LinkedIn posts, company social media, and news articles—so it will read untrusted, user-generated web content as part of its Phase 1 research.