job-market-intel

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

• Third-party content exposure detected (high risk: 1.00). This skill explicitly runs TinyFish agents to fetch and scrape live job postings from untrusted public sites (LinkedIn, Indeed, Glassdoor) as shown in Step 1–3 ("Search LinkedIn Jobs", "Search Indeed", "Search Glassdoor" with tinyfish agent run --url ...), and the agent must parse and synthesize those pages into actionable market and negotiation guidance.