mcp-server-skills
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- Input Validation (SAFE): The skill correctly uses Zod for schema validation (
diceSchema.parse(sides)). This ensures that inputs are checked for type and range before processing, preventing potential logic errors or injection attempts through user-supplied parameters. - External Dependencies (LOW): The skill references
mcp-handlerandmcp-remotevia NPM. While these authors are not on the specific Trusted Organizations list, the packages are standard utilities in the MCP community and are used as intended for development patterns. The [TRUST-SCOPE-RULE] applies as they are standard references for the skill's primary purpose. - Command Execution (SAFE): No dangerous shell commands or privilege escalation attempts were found. The provided configuration for Claude Desktop uses
npxto run a known bridge utility, which is the standard method for local MCP server connection. - Data Privacy (SAFE): No hardcoded credentials, sensitive file access, or unauthorized network operations were identified. The logic is self-contained and focuses on a simple dice-rolling implementation.
Audit Metadata