agent-token-efficiency
Warn
Audited by Gen Agent Trust Hub on Jul 24, 2026
Risk Level: MEDIUMREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The installation guide in
references/tools-install.mdincludes a command for the 'Caveman' tool that downloads a PowerShell script from a remote URL (https://raw.githubusercontent.com/JuliusBrussee/caveman/main/install.ps1) and executes it immediately using theiex(Invoke-Expression) command, bypassing local security review. - [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install several third-party components from unverified GitHub repositories and package registries, specifically
DietrichGebert/ponytail,JuliusBrussee/caveman, and theheadroom-aiPython package. - [COMMAND_EXECUTION]: The skill promotes the use of 'Headroom' (
headroom wrap cursor), which acts as a local proxy to intercept and modify traffic between the AI agent and the model provider. This introduces a significant trust dependency on unverified third-party software that handles all model communication. - [COMMAND_EXECUTION]: The skill utilizes
npx skills addcommands to fetch and install external modules from various GitHub accounts, which can lead to the execution of unverified remote code in the local environment.
Audit Metadata