process-issues

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

• Third-party content exposure detected (high risk: 1.00). The skill explicitly fetches and reads user-generated GitHub content (e.g., via "gh pr view --comments" and "gh api repos/.../pulls//comments" and "gh issue view") and then uses those comments and issue bodies to drive decisions and invoke the code-implementation workflow, creating a direct vector for untrusted third-party content to influence agent actions.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill calls GitHub API endpoints at runtime (e.g., gh api repos/$REPO/pulls//comments -> https://api.github.com/repos/$REPO/pulls//comments) to fetch PR/issue comments which are then parsed and used to drive the agent's actions, so remote user-written content can directly influence prompts and behavior.