prose-gen
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a pure instruction-based generator for the OpenProse DSL. It provides a comprehensive reference for syntax including agents, sessions, and loops.
- [PROMPT_INJECTION]: The instructions are strictly focused on code generation and syntax adherence. No override, bypass, or extraction patterns were found.
- [DATA_EXFILTRATION]: The skill does not define any operations that access sensitive file paths (e.g., SSH keys, credentials) or perform unauthorized network requests.
- [REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of external scripts (e.g., curl | bash). All code generation is static text based on a provided schema.
- [COMMAND_EXECUTION]: While the DSL reference mentions a 'bash' permission setting for generated agents, the skill itself does not execute system commands or shell scripts.
Audit Metadata