implement

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly runs gh issue view ... --json ... to fetch an issue's title, body and comments from the repository's GitHub issues (SKILL.md step 1) and instructs the agent to read those issue contents and comments to determine implementation decisions (SKILL.md step 2), which are untrusted, user-generated third-party content that can influence actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill runs git remote get-url origin (e.g., git@github.com:org/repo.git or https://github.com/org/repo.git) and then executes gh issue view at runtime to fetch issue text from GitHub (via api.github.com), and that fetched issue content is directly used to control the agent's implementation instructions.