alterlab-nmc-digital-ethics

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly requires the agent to "Search the web" and use public OSINT tools (InVID/WeVerify, Google Fact Check Tools API, Wayback Machine, TinEye/Google Reverse Image Search) and to read public misinformation case studies and social/platform content as part of its required research and deliverable workflow, which exposes it to untrusted third‑party, user‑generated content that can materially influence actions.