ai-tooling-stack
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to perform or recommend installations of external software via standard package registries, specifically using
pip install headroomandnpx codeburn. - [COMMAND_EXECUTION]: The skill includes instructions for the agent to execute local PowerShell scripts for system setup and tool orchestration, including
.\INSTALL-AIO.ps1,.\TOOLS\Setup-HouseCarl.ps1, and.\TOOLS\Ensure-Tools.ps1. - [REMOTE_CODE_EXECUTION]: The skill references a specific maintenance script,
.\TOOLS\Update-From-GitHub.ps1, which is intended to fetch and apply code updates from a remote GitHub repository to the local environment. - [INDIRECT_PROMPT_INJECTION]: The skill processes data from various external modding tools and CLI outputs, creating an attack surface for indirect prompt injection.
- Ingestion points: Processes output from
houseCARLload-order trees,Headroomcontext logs, and Forge CLI diagnostic reports. - Boundary markers: No specific delimiters or instructions to ignore embedded instructions within tool outputs are defined in the skill text.
- Capability inventory: The agent possesses the capability to execute PowerShell scripts, manage packages via
pipandnpx, and modify files within mod project directories. - Sanitization: There are no documented procedures for sanitizing or validating the content returned by external binaries before it is processed by the agent.
Audit Metadata