rfc
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill behaves exactly as described, facilitating document creation through a conversational interface.
- [PROMPT_INJECTION]: The instructions do not contain attempts to override safety filters, extract system prompts, or bypass AI constraints.
- [COMMAND_EXECUTION]: No shell commands, subprocess calls, or dangerous scripts were identified in the skill logic.
- [EXTERNAL_DOWNLOADS]: The skill does not download external packages or execute remote code; it relies entirely on local templates and user input.
- [DATA_EXFILTRATION]: There are no network operations or accesses to sensitive file paths (such as credentials or SSH keys). The skill writes generated artifacts to a standard output directory.
Audit Metadata