hive-mind-advanced

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly integrates with GitHub (see "With GitHub Integration" — e.g., "Analyze repo quality" with --objective "owner$repo" and PR review spawns), which means the agent will fetch and analyze arbitrary public repositories and pull requests (user-generated, untrusted content) as part of its workflow.