skill-authoring
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The skill consists entirely of markdown documentation and YAML metadata. It does not contain any executable scripts, shell commands, or logic triggers.
- [PROMPT_INJECTION] (SAFE): No attempts to override system prompts, bypass safety filters, or use adversarial role-play patterns were identified.
- [DATA_EXFILTRATION] (SAFE): The skill references local configuration paths (e.g., ~/.config/opencode) only for the purpose of explaining where to place files; it does not perform any file read operations or network requests.
- [EXTERNAL_DOWNLOADS] (SAFE): No remote scripts, external APIs, or package registries are accessed or referenced for download.
Audit Metadata