ai-do
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a non-executable, text-based utility used for routing and categorization. It contains no scripts, binaries, or external code components.
- [PROMPT_INJECTION]: The instructions in
SKILL.mdare designed to assist the user and do not contain any patterns for bypassing safety filters, extracting system prompts, or overriding agent constraints. - [DATA_EXFILTRATION]: The skill does not access sensitive local file paths (such as credentials or SSH keys) and has no network communication capabilities.
- [REMOTE_CODE_EXECUTION]: There are no remote code patterns, such as downloading and executing scripts from external URLs or installing unverifiable packages.
Audit Metadata