github-do-issue

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

• Third-party content exposure detected (medium risk: 0.30). The workflow fetches outsider-authored GitHub issue content (issue body and comments) via gh issue view ... --json ... body ... comments in Step 1 and then uses it to drive requirements planning.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill fetches GitHub issue content at runtime (e.g., https://github.com/owner/repo/issues/42) via gh issue view and then uses the issue body and comments to drive what the agent implements, so external content directly controls the agent's prompts/behavior.