copilot-sdk-dotnet

Warn

Audited by Snyk on Mar 9, 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). The skill explicitly documents connecting to remote MCP servers (references/mcp-integration.md and SKILL.md) via HTTP/SSE URLs and using their tool results (Tools = "*" / "search") which the agent consumes as tool outputs for reasoning, so untrusted third-party content from those servers could supply instructions that materially influence agent behavior.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 9, 2026, 11:17 PM