codebase-exploration

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

• Third-party content exposure detected (low risk: 0.10). The required workflow reads GitHub repository content (file contents, directory trees, code search results, and commit messages and diffs) from a repository the agent selects, and that content can be authored by outside contributors, so the agent must actively fetch it, which makes this low rather than medium because the skill does not read issues, PRs, or other monitored outsider queues.