unity-script

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides tools to read, search, and parse existing C# scripts, which could contain malicious instructions designed to influence the agent's behavior during refactoring or code generation tasks.
  • Ingestion points: The script_read and script_find_in_file skills ingest content from existing project files (SKILL.md).
  • Boundary markers: The instructions do not specify any delimiters or safety warnings for the agent to ignore instructions embedded within the C# code it processes.
  • Capability inventory: The skill includes powerful modification and destructive capabilities, including script_create, script_replace, script_append, script_delete, script_rename, and script_move (SKILL.md).
  • Sanitization: There is no mention of content sanitization or safety checks for the content being read or subsequently written to the filesystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 06:51 AM