skill

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

• Third-party content exposure detected (high risk: 1.00). The skill's "/skill setup" Import Skill option explicitly lets the agent download a skill from an arbitrary URL (e.g., "GitHub gist") or accept pasted content, so the agent will fetch and parse untrusted third-party/user-provided markdown that it must read and interpret.