onboarding

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill files consist entirely of Markdown-formatted instructions, reference tables, and JSON evaluation data. No scripts (.py, .js, .sh) or executable binaries are included.
  • [DATA_EXFILTRATION]: There are no network operations, API calls, or commands that send data to external servers. All operations are confined to the local interaction between the user and the agent.
  • [COMMAND_EXECUTION]: No shell commands, subprocess calls, or automated terminal executions are defined in the instructions or metadata.
  • [DATA_EXPOSURE]: The skill requests reading project-specific marketing context from files such as .agents/product-marketing.md. This is a standard procedure for gathering task-relevant information and does not target sensitive user data like SSH keys or environment secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 01:05 PM
Security Audit — agent-trust-hub — onboarding