azure-hosted-copilot-sdk

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

• Third-party content exposure detected (high risk: 0.80). The skill's documentation (references/copilot-sdk.md "Getting Current Examples") explicitly instructs the agent to call context7-resolve-library-id and context7-query-docs and to fall back to github-mcp-server-get_file_contents to read files from the public GitHub repo (github/copilot-sdk), meaning the agent fetches and interprets open, user-generated third‑party content that can materially influence its actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs using runtime MCP/fallback calls (e.g., github-mcp-server-get_file_contents against the repo https://github.com/github/copilot-sdk) to fetch code/docs snippets which are then selected and injected into the agent context, so external content fetched at runtime can directly control prompts and behavior.