openspec-new-change
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements restricted execution via the
allowed-toolsconfiguration, limiting Bash commands strictly to theopenspec:*namespace. - [SAFE]: Instructions include mandatory validation steps for user-provided names (enforcing kebab-case) and utilize double-quoting in shell command templates to mitigate potential command injection vulnerabilities.
- [SAFE]: No network exfiltration, unauthorized file system access, or remote script execution patterns were detected.
- [SAFE]: The operations described are consistent with the primary purpose of the skill as a development tool, and no obfuscated or malicious code was found.
Audit Metadata