prompt-boost
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill instructions focus on iterative prompt refinement and organization without requesting sensitive permissions.
- [PROMPT_INJECTION]: No evidence of jailbreak attempts, system prompt extraction, or safety override commands was found.
- [DATA_EXFILTRATION]: There are no patterns indicating the collection or transmission of sensitive data to external servers.
- [REMOTE_CODE_EXECUTION]: The skill explicitly forbids the agent from writing code and contains no shell commands or script execution logic.
Audit Metadata