skills/amd/skills/local-ai-use/Gen Agent Trust Hub

local-ai-use

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The setup_local_ai.py script downloads installer packages from the lemonade-sdk repository on GitHub.
  • It retrieves .msi files for Windows and .pkg files for macOS using the urllib.request library.
  • It queries the GitHub API to resolve the latest versioned download links for the target operating system.
  • [REMOTE_CODE_EXECUTION]: The skill executes the downloaded binary installers to set up the local server daemon.
  • On Windows, it runs msiexec to perform a silent installation of the .msi package.
  • On macOS, it utilizes the system installer utility to process the downloaded .pkg file.
  • [COMMAND_EXECUTION]: The setup script executes shell commands to configure the environment and manage system services.
  • It uses sudo on Linux and macOS to perform system-level installations and service management tasks.
  • It uses subprocess.run with shell=True on Linux to execute a command pipeline that adds a PPA and installs the server via apt-get.
  • [PROMPT_INJECTION]: The skill modifies the workspace's AGENTS.md file to persist local routing instructions for the agent, which represents an indirect prompt injection surface.
  • Ingestion points: The script writes directly to AGENTS.md in the workspace root, which is automatically read by many agent platforms.
  • Boundary markers: The injected instructions are wrapped in stable <!-- BEGIN/END --> HTML comments to ensure updates are idempotent and correctly delimited.
  • Capability inventory: The skill has the capability to download files, execute system commands, and modify local configuration files.
  • Sanitization: It utilizes static templates for instructions, interpolating only validated configuration values such as port numbers and predefined model IDs rather than raw user input.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 03:20 AM
Security Audit — agent-trust-hub — local-ai-use