console-clear-logs
Pass
Audited by Gen Agent Trust Hub on Aug 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to perform its core function by executing the
unity-mcp-clicommand in the shell environment. - [EXTERNAL_DOWNLOADS]: The instructions suggest installing the
unity-mcp-clipackage globally via npm or usingnpx, resulting in the download and execution of code from the public npm registry. - [PROMPT_INJECTION]: The skill defines a tool interface that accepts external parameters, creating a surface for potential indirect instruction injection. * Ingestion points: The
nothingfield within the tool's input JSON schema in SKILL.md. * Boundary markers: There are no explicit delimiters or instructions to prevent the agent from following directives potentially embedded in the input strings. * Capability inventory: The skill possesses the ability to execute shell commands and interact with the Unity Editor environment. * Sanitization: The documentation does not specify any sanitization, filtering, or validation processes for the input data.
Audit Metadata