crafting-instructions
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill is a meta-utility for generating instructions but explicitly contains a 'Trust Base Behavior' section that reinforces adherence to core safety guidelines, copyright protocols, and ethical standards. No malicious bypasses or overrides were identified.
- [COMMAND_EXECUTION]: The skill includes shell command examples (e.g., zip, mkdir, git) in its documentation files. These are presented as educational snippets for users to organize and package their own skills and do not represent autonomous or malicious execution by the agent.
- [EXTERNAL_DOWNLOADS]: References provided in the documentation point exclusively to official Anthropic documentation and well-known, trusted tutorial repositories. These are used for informational purposes and do not trigger unauthorized downloads.
- [DATA_EXFILTRATION]: No sensitive file paths, hardcoded credentials, or unauthorized network operations were detected. The skill focuses on text generation based on user input.
- [OBFUSCATION]: All content is written in plain Markdown. There are no instances of Base64 encoding, zero-width characters, or other techniques used to hide malicious intent.
Audit Metadata