bonfire-review-pr

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

• Third-party content exposure detected (high risk: 0.80). The skill fetches and reads PR metadata, the PR body, and the changed files from GitHub (via gh pr view and by checking out the PR worktree), which are untrusted, user-generated third-party contents that the agent is expected to read and interpret as part of its review workflow.