AGENT LAB: SKILLS

copilot-sdk

Warn

Audited by Snyk on Feb 15, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). This SDK explicitly supports connecting to external MCP servers (see "MCP Server Integration" with "https://api.githubcopilot.com/mcp/") and defining tools that fetch repository/issue/PR and other user-generated content, which the agent will read and incorporate into its responses, exposing it to untrusted third‑party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:15 PM