connect-ai-onboarding-claude-code

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to open browser windows to official vendor websites (cdata.com) and to interact with the claude CLI for server registration. These operations are standard for a configuration and onboarding skill.
  • [EXTERNAL_DOWNLOADS]: The skill directs users to official CData Software domains (cdata.com, cloud.cdata.com) to facilitate account creation and data source setup. These resources are consistent with the skill's purpose and belong to the verified author.
  • [CREDENTIALS_SAFE]: The skill demonstrates high security awareness by explicitly instructing the agent not to handle user credentials. Instead, it provides commands for the user to run in their own terminal, ensuring that sensitive Personal Access Tokens are never entered into the AI session or stored in the conversation history.
  • [INDIRECT_PROMPT_INJECTION]: The skill accesses metadata from a connected service via the getCatalogs tool to verify connectivity. The risk is minimal as the agent only performs a read-only operation to list available data catalogs for display to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 04:49 PM
Security Audit — agent-trust-hub — connect-ai-onboarding-claude-code