script-creation-rules
Pass
Audited by Gen Agent Trust Hub on Feb 19, 2026
Risk Level: SAFE
Full Analysis
- COMMAND_EXECUTION (SAFE): The skill encourages the use of standard shell one-liners for tasks like file searching and text processing. All provided examples (find, grep, sed, wc) are benign and follow standard practices.\n- EXTERNAL_DOWNLOADS (SAFE): The skill explicitly prohibits Node.js and Python, which effectively prevents the use of external package managers like npm and pip, reducing the risk of dependency-based attacks.\n- DYNAMIC_EXECUTION (SAFE): The skill facilitates script generation using Deno but mandates the use of a specific security wrapper ('sfw') and explicit permission flags, indicating a security-conscious approach to execution.\n- PROMPT_INJECTION (SAFE): While the skill uses strong language like 'MUST ALWAYS' and 'CRITICAL', these terms define operational guidelines for the agent rather than attempting to bypass safety filters or override system-level instructions.
Audit Metadata