Skills
skills/abilityai/abilities/trinity-onboard/Gen Agent Trust Hub

trinity-onboard

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: Uses Bash scripts to inspect the local filesystem, initialize Git repositories, and package the agent's source code using tar and base64 for deployment.
  • [EXTERNAL_DOWNLOADS]: Configures an MCP server that uses npx to dynamically load the mcp-remote package and connect to a user-specified Trinity instance URL.
  • [CREDENTIALS_UNSAFE]: Collects sensitive Trinity API keys and URLs via user prompts, storing them in local .env and .mcp.json files. It includes a safety mechanism that automatically updates .gitignore to prevent these credentials from being committed to version control.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 11:46 PM