hiring-signal-outreach

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

• Third-party content exposure detected (high risk: 0.90). The skill's Step 1 "Detect Hiring Signals" explicitly instructs the agent to search and fetch job postings from public sites (LinkedIn Jobs, Indeed, Google Jobs, web search) and to extract and interpret job description summaries and source URLs, and those third-party postings are then used to classify signals and drive prioritization and personalized outreach, meaning untrusted public content can materially influence agent decisions.