hiring-signal-prospector

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

• Third-party content exposure detected (high risk: 0.95). Outsider-authored free text is ingested when the workflow runs WebSearch/WebFetch to retrieve public job posting pages (and then extracts JD snippets/responsibilities/requirements) from third parties, which are then placed into the agent’s LLM context for analysis and reporting.