cc-explorer

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

• Third-party content exposure detected (high risk: 0.90). The skill's Task instructs the cc-explorer agent to fetch public documentation and a changelog from code.claude.com (starting at code.claude.com/docs/llms.txt and "systematically fetch all relevant documentation pages") and to read and synthesize those pages as part of its workflow, so untrusted third-party web content can directly influence its outputs and actions.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill's cc-explorer agent explicitly fetches and ingests external documentation at runtime from code.claude.com/docs/llms.txt, which will be injected into the agent's context and therefore directly control prompts/outputs (flagging URL: https://code.claude.com/docs/llms.txt).