alterlab-nmc-newsletter

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

• Third-party content exposure detected (high risk: 0.90). The skill's required execution and workflow explicitly instruct the agent to autonomously "search the web" and ingest public sources (e.g., "Execution Mode: Autonomous — you search the web..." and Workflow steps that call for "Search the web", RSS readers, and Twitter lists), meaning untrusted, user-generated third-party content is read and used to drive decisions and actions.