enrich-and-research

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md workflow explicitly fetches and displays user-generated public content (e.g., "Social signals" with post_content and source_url, "Hiring signals" from job postings) via the OpenFunnel API (api.openfunnel.dev) and the deep-enrich flow ("Scans job postings, social activity"), and those signals are then interpreted and used to drive the Attack Strategy—meeting all criteria for untrusted third‑party content influencing agent decisions.