expansion-signal-spotter

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md Phase 1 instructions and Tools Required section explicitly direct the agent to use web_search, fetch_webpage, linkedin-profile-post-scraper, and job-posting-intent to ingest LinkedIn posts, job postings, news and public company pages (open/public, user-generated/untrusted content) which the agent reads and uses to score opportunities and decide next actions, creating a clear vector for indirect prompt injection.