azure-hosted-copilot-sdk
Build and deploy GitHub Copilot SDK apps to Azure. WHEN: build copilot app, create copilot app, copilot SDK, @github/copilot-sdk, scaffold copilot project, copilot-powered app, deploy copilot app, host on azure, azure model, BYOM, bring your own model, use my own model, azure openai model, DefaultAzureCredential, self-hosted model, copilot SDK service, chat app with copilot, copilot-sdk-service template, azd init copilot, CopilotClient, createSession, sendAndWait, GitHub Models API.
90
87%
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 required workflow explicitly instructs the agent to fetch and read public GitHub content (e.g., references/copilot-sdk.md directs using context7-resolve-library-id / context7-query-docs and falling back to github-mcp-server-get_file_contents on the public repos like "github/copilot-sdk" and "azure-samples/copilot-sdk-service"), which causes the agent to ingest untrusted, user-controlled third-party content that can influence subsequent code-selection and deployment 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 the agent to call runtime MCP tools (e.g., context7 queries and the fallback github-mcp-server-get_file_contents) to read files from the GitHub repo https://github.com/github/copilot-sdk and then "select the most relevant snippets" to use in the user's scenario, meaning fetched remote content is pulled at runtime and can be injected into the model context to control prompts.
- Repository
- microsoft/github-copilot-for-azure
- Commit
1f4304b
- 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.