getting-started
Pass
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is defensive and procedural in nature, focusing on improving the agent's decision-making and data-handling integrity. No malicious patterns, obfuscation, or unauthorized commands were detected.
- [PROMPT_INJECTION]: The skill contains specific instructions to defend against prompt injection by prioritizing internal rules and process skills over user requests that attempt to rationalize skipping quality gates. It explicitly warns the agent against accepting 'simple feature' or 'urgent' rationales as reasons to bypass process.
- [DATA_EXFILTRATION]: No data exfiltration patterns were found. The skill defines a hierarchy for accessing local configuration files (e.g., settings.json) but does not include instructions for external transmission of this data.
- [REMOTE_CODE_EXECUTION]: No remote code execution or suspicious package installation patterns were identified.
Audit Metadata