Skills
Navigate
skills/idocohen560/claude-unity-game-studio/assets-prefab-open/Gen Agent Trust Hub

assets-prefab-open

Pass

Audited by Gen Agent Trust Hub on Sep 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts complex JSON input that is interpolated into a shell command, creating a surface where malicious data could attempt to override agent behavior.
  • Ingestion points: gameObjectRef parameter in SKILL.md.
  • Boundary markers: None present.
  • Capability inventory: Shell command execution of unity-mcp-cli as shown in SKILL.md.
  • Sanitization: No input sanitization or validation is defined.
  • [COMMAND_EXECUTION]: The skill uses the unity-mcp-cli tool to perform actions by executing shell commands with user-provided arguments.
  • [EXTERNAL_DOWNLOADS]: The skill instructions suggest installing the unity-mcp-cli package via npm, which involves downloading and installing third-party code.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 29, 2026, 04:32 PM