alterlab-nmc-media-theory

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to "search the web for academic databases, recent journal articles, and scholarly debates" (see "Execution Mode" and "Agentic Protocol"), meaning it fetches and reads open/public third‑party content which the agent is expected to interpret and use to drive its decisions and outputs.