Skills
skills/microsoft/copilot-sdk-samples/mcp-builder/Snyk

mcp-builder

Warn

Audited by Snyk on Jun 19, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (medium risk: 0.65). The evaluation harness (scripts/evaluation.py) calls connection.call_tool(...), and for SSE/HTTP transports the MCP server can return arbitrary free-text in result.content which is then appended into the agent’s messages context (indirect prompt injection via outsider-authored tool output).

Issues (1)

W011
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 19, 2026, 10:35 PM
Issues
1
Security Audit — snyk — mcp-builder