fetch-diff

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

• Third-party content exposure detected (high risk: 0.95). At runtime, the skill fetches outsider-authored PR content from GitHub via GitHubClient.get_pr() / get_pr_diff() (public web content) and passes the resulting diff text into filter_diff(), which returns it as readable text for the agent/LLM context.