unity-cleaner

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions do not contain any known malicious patterns, obfuscation, or unauthorized data exfiltration.
  • [COMMAND_EXECUTION]: The skill facilitates project maintenance through file system operations like asset scanning and deletion. Destructive actions are guarded by a confirmation token system and a safety-first dry-run policy.
  • [DATA_EXFILTRATION]: While the skill reads project structure and asset metadata (paths, hashes, sizes), there are no network operations or external destinations defined for this data.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection from untrusted project files. 1. Ingestion points: Project file paths and content in the Assets directory (SKILL.md). 2. Boundary markers: None explicitly defined. 3. Capability inventory: cleaner_delete_assets and cleaner_delete_empty_folders. 4. Sanitization: None explicitly defined. These factors are considered low risk as the operations are consistent with the skill's primary cleanup purpose and require confirmation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 10:15 AM