tldr-prompt

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

• Third-party content exposure detected (high risk: 1.00). The skill's URL Resolver and Workflow explicitly require fetching public web content (e.g., raw.githubusercontent.com for github/awesome-copilot files and documentation from https://code.visualstudio.com and https://modelcontextprotocol.io) and then reading and using that untrusted, user-authored content to generate TLDRs, so third‑party pages can influence the agent's actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches remote content at runtime (e.g., https://raw.githubusercontent.com/github/awesome-copilot/refs/heads/main/{{folder}}/{{filename}} — and also documentation URLs such as https://code.visualstudio.com/docs/copilot/customization/mcp-servers and https://modelcontextprotocol.io/) and injects that fetched content into the agent context to drive/tailor prompts, so these runtime fetches directly control agent instructions.