plan

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly runs gh issue view to fetch GitHub issue content (public, user-generated) and uses that issue text to analyze requirements and drive implementation decisions and write tasks, so untrusted third-party content can directly influence agent actions.

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

• Potentially malicious external URL detected (high risk: 1.00). This skill calls gh issue view to fetch a GitHub issue at runtime (e.g., https://github.com/owner/repo/issues/123), and the fetched issue content is used to generate and control the agent's planning instructions, so the external URL is a runtime dependency that can directly control prompts.