refactor-skill

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches documentation pages and a specific GitHub raw file, representing trusted or developer-authored content rather than monitored outsider feeds.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill instructs the agent at runtime to fetch raw instructions and guidelines from external URLs like https://raw.githubusercontent.com/mattpocock/skills/main/skills/productivity/writing-for-agents/SKILL.md to calibrate its behavior and actions.