assets
Pass
Audited by Gen Agent Trust Hub on Jul 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: Recommends the installation of the @agent-native/core and skills packages from NPM via npx for setup and MCP connector management.
- [COMMAND_EXECUTION]: Provides specific CLI commands for initial setup, connecting to remote MCP endpoints, and re-authenticating sessions.
- [DATA_EXFILTRATION]: Includes strong security guardrails that explicitly instruct the agent to redact sensitive Authorization headers, http_headers, and bearer tokens if inspecting local configuration files.
- [SAFE]: The skill emphasizes the use of host-exposed tools and discourages manual HTTP requests or direct provider calls, maintaining a secure execution boundary.
Audit Metadata