employer-matching

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly references ingesting open/public third-party content—e.g., "job posting ingestion: ... job board scraping" (Phase 1.3), employee reviews/culture sources (Phase 4.1), and external salary providers like Glassdoor/BLS/Levels.fyi (Phase 7.1)—which the agent is expected to read and use to influence matching decisions, so untrusted user-generated web content could inject instructions indirectly.