alterlab-nmc-social-analyst

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly instructs the agent to "Search the web" and "Research first" (see "Workflow" Step 1 and "Agentic Protocol") to fetch current platform demographics, algorithm updates and analytics from the public web/social platforms — untrusted third-party content the agent is expected to read and use to drive analysis and recommendations, which can materially influence its actions.