mcp

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.90). The skill invokes external MCP servers at runtime by executing remote packages (e.g., npx -y @github/mcp-server, uvx codebase-memory-mcp@latest) and may contact external endpoints such as https://mcp.figma.com/mcp, which causes fetching/execution of remote code or remote control of agent behavior.

MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).

• Hidden Unicode characters detected (1 type(s) found)