make-it-a-skill

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

• Third-party content exposure detected (high risk: 0.70). SKILL.md (Step 3 and the "Walked Example") explicitly describes scheduled tasks fetching inputs via GitHub and Linear APIs and Slack threads (user-generated third-party content) which the agent is expected to read/interpret to produce posts/invoke skills, allowing those external contents to influence agent behavior.