claude-code-dev
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- NO_CODE (SAFE): The skill consists solely of Markdown instructions and directory structure templates. There are no executable scripts (.sh, .py, .js) or automated command sequences included.- EXTERNAL_DOWNLOADS (SAFE): The skill references official documentation (code.claude.com) and the 'anthropics' GitHub organization. These are trusted sources according to the analysis guidelines, and no automated downloads or piped executions (e.g., curl|bash) are performed.- PROMPT_INJECTION (SAFE): The instructions do not contain attempts to override system prompts, bypass safety filters, or extract sensitive instructions.- DATA_EXFILTRATION (SAFE): No code exists to read sensitive files (such as SSH keys or environment variables) or exfiltrate data to external domains.- CREDENTIALS_UNSAFE (SAFE): No hardcoded API keys, passwords, or secrets were found in the skill content.
Audit Metadata