pr-implement

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs fetching and inspecting open GitHub PRs/issues in "Phase -1: Prior Work Check" (using commands like gh pr list and gh issue view), which pulls untrusted, user-generated content that the workflow must read and act on and therefore could carry indirect prompt-injection risk.