skill-lookup

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

• Third-party content exposure detected (high risk: 0.90). This skill calls the prompts.chat MCP server tools (search_skills and get_skill) to retrieve full skill packages including SKILL.md, scripts, and config files authored by external users, so untrusted user-generated content from those third-party skill pages would be ingested and could influence agent actions (e.g., installation and execution) at runtime.