sdk-scaffolder
Pass
Audited by Gen Agent Trust Hub on Mar 3, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: No evidence of jailbreak attempts, instruction overrides, or safety filter bypasses in the skill instructions.
- [CREDENTIALS_UNSAFE]: No real secrets or sensitive file paths are exposed; code examples use clearly marked placeholders (e.g., 'sk_test...').
- [REMOTE_CODE_EXECUTION]: No patterns for downloading and executing remote scripts or code were detected.
- [COMMAND_EXECUTION]: No dangerous system commands, shell operations, or privilege escalation patterns are present in the skill definition.
- [EXTERNAL_DOWNLOADS]: The skill does not initiate external downloads or rely on unverified third-party dependencies.
Audit Metadata