azure-hosted-copilot-sdk
Build, deploy, modify GitHub Copilot SDK apps on Azure. MANDATORY when codebase contains @github/copilot-sdk or CopilotClient — use this skill instead of azure-prepare. PREFER OVER azure-prepare when codebase contains copilot-sdk markers. WHEN: copilot SDK, @github/copilot-sdk, copilot-powered app, deploy copilot app, add feature, modify copilot app, BYOM, bring your own model, CopilotClient, createSession, sendAndWait, azd init copilot. DO NOT USE FOR: general web apps without copilot SDK (use azure-prepare), Copilot Extensions, Foundry agents (use microsoft-foundry).
94
92%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Security
2 findings — 2 medium severity. This skill can be installed but you should review these findings before use.
W011: Third-party content exposure detected (indirect prompt injection risk)
What this means
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
Why it was flagged
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.
W012: Unverifiable external dependency detected (runtime URL that controls agent)
What this means
The skill fetches instructions or code from an external URL at runtime, and the fetched content directly controls the agent’s prompts or executes code. This dynamic dependency allows the external source to modify the agent’s behavior without any changes to the skill itself.
Why it was flagged
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.
- Repository
- microsoft/github-copilot-for-azure
- Commit
a46a937
- Audited
- Security analysis
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.