NYC

skill-creator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • COMMAND_EXECUTION (SAFE): The Python scripts package_skill.py and quick_validate.py perform local file system operations using standard libraries (pathlib, zipfile, re). These operations are restricted to validating skill structure and creating ZIP archives.
  • DATA_EXFILTRATION (SAFE): The packaging utility reads local files to create an archive, but it contains no network communication code (e.g., requests, urllib, socket) and does not transmit data to external servers.
  • EXTERNAL_DOWNLOADS (SAFE): The scripts do not download or execute any remote content. All dependencies are standard Python libraries, and no package manager calls (pip, npm) are performed.
  • PROMPT_INJECTION (SAFE): No malicious instructions or bypass attempts were found in the SKILL.md (implied structure) or the sanitization checklist documentation.
  • REMOTE_CODE_EXECUTION (SAFE): There are no instances of eval(), exec(), or subprocess calls that handle untrusted input. The scripts are straightforward utility tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:08 PM