plot-deliver

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow (Step 5) explicitly launches subagents that run gh pr diff and gh pr view to read PR bodies, diffs, and metadata from GitHub (user-generated PRs), and those readings are used to judge completeness and drive delivery actions, which exposes the agent to untrusted third-party content that could inject instructions.