resolve-pr-parallel

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and ingests user-generated GitHub PR review threads (via scripts/get-pr-comments using gh api GraphQL and the SKILL.md "Fetch and Summarize unresolved review threads" workflow) and the agent is expected to read and act on those comments to plan and execute remediation, so untrusted third-party content can materially influence actions and enable indirect prompt injection.