fusion360-expert

Pass

Audited by Gen Agent Trust Hub on Mar 20, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill uses standard role-play instructions to define the AI's persona as a Fusion 360 expert. No instructions to bypass safety filters or override system constraints were found.
  • [DATA_EXFILTRATION]: No network requests to unauthorized domains or attempts to access sensitive local files (like credentials or configuration files) were detected.
  • [REMOTE_CODE_EXECUTION]: No patterns of downloading and executing remote scripts or dynamic code execution through unsafe functions were found.
  • [OBFUSCATION]: All content is in plain text and relates directly to the stated purpose. No hidden characters, encoded strings, or homoglyph techniques were detected.
  • [EXTERNAL_DOWNLOADS]: The skill references its own source code on GitHub for installation and provides links to official Autodesk documentation. These resources are legitimate and associated with the vendor's stated infrastructure and the skill's primary function.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 20, 2026, 06:47 PM