Skills
skills/codealive-ai/ai-driven-development/mcp-management/Gen Agent Trust Hub

mcp-management

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses administrative commands like claude mcp add and npx add-mcp to manage agent extensions. These actions are triggered by user requests and follow established protocol standards.
  • [EXTERNAL_DOWNLOADS]: The skill retrieves configuration and installation packages from established sources like npm and official vendor repositories (e.g., GitHub, Stripe, Sentry). It includes a verification workflow to ensure servers are from official sources before installation.
  • [SAFE]: The skill demonstrates high security awareness by explicitly warning users about the risks of prompt injection in third-party servers and requiring manual confirmation for removal of configurations.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 11:48 PM