visual-explainer

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows (e.g., prompts/diff-review.md and plan-review.md) explicitly instruct the agent to fetch and read user-generated GitHub/PR content and repository files (commands like gh pr diff 42, git show <ref>:file, reading PR descriptions/commit messages and changed files), so the agent ingests untrusted third-party content that can influence its decisions and actions.