api-design-coach
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely composed of natural language instructions and structural guidance for a coaching interaction. It does not include any scripts, commands, or automation logic.
- [REMOTE_CODE_EXECUTION]: There are no patterns for remote code execution, external downloads, or package installations. All behavior is limited to text generation.
- [DATA_EXFILTRATION]: The skill does not contain any network operations or commands to access sensitive local files. It includes a reference to a local memory file (
SKILL_MEMORY.md), which is a standard pattern for persistent agent context. - [PROMPT_INJECTION]: The instructions include strict 'Hard Refusals' that prevent the agent from generating code, specs, or specific naming suggestions, effectively narrowing the attack surface for prompt-based manipulation.
- [DYNAMIC_CONTEXT_INJECTION]: No dynamic execution placeholders (such as shell command substitution) are present in the skill definition.
Audit Metadata