gh-cli-agentic

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

• Third-party content exposure detected (high risk: 0.85). The required runtime workflow uses gh issue view ... --json ... comments / gh pr view ... --json ... body / gh run view ... --log which ingests outsider-authored GitHub issue/PR text (e.g., comments, PR body, failed logs) into the agent’s LLM context via the CLI output.