init-agent-config
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified during the analysis.
- [PROMPT_INJECTION]: The skill contains no instructions that attempt to override safety protocols or jailbreak the agent. Directional language used (e.g., 'CRITICAL', 'IMPORTANT') is appropriately context-bound to configuration quality and repository safety.
- [CREDENTIALS_UNSAFE]: The skill explicitly instructs agents to perform a cross-check to ensure 'no secrets or credentials' are included in the generated configuration files.
- [REMOTE_CODE_EXECUTION]: All command patterns provided for auditing are standard local operations (e.g., cat, grep, jq) used to inspect project manifests and do not involve executing untrusted remote code.
- [DATA_EXFILTRATION]: There are no patterns suggesting unauthorized network activity or data exfiltration.
- [SAFE]: The skill addresses the potential risk of indirect prompt injection by instructing the agent to preserve existing boundary rules and verify all facts against the repository's code.
Audit Metadata