metavr-cli

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves external content from Meta Quest developer documentation using the metavr docs fetch tool. This content is then processed by the agent to assist with development tasks, creating a potential injection surface.
  • Ingestion points: Documentation search and retrieval commands metavr docs search and metavr docs fetch (SKILL.md and references/metavr-docs-search.md).
  • Boundary markers: The documentation includes safety guidance in references/metavr-agent-workflows.md which advises the agent to treat fetched documentation and tool outputs as untrusted data.
  • Capability inventory: The skill allows interaction with the metavr CLI, which supports app installation, device rebooting, and shell access (metavr adb shell) on Quest headsets (references/metavr-device-management.md).
  • Sanitization: The instructions recommend human-in-the-loop approvals for sensitive actions like uninstalling apps, but do not specify technical sanitization for the documentation content.
  • [COMMAND_EXECUTION]: The skill provides mechanisms for executing shell commands on connected Android-based devices.
  • Evidence: The skill documentation provides examples for using metavr adb shell and metavr shell to run arbitrary commands on the headset's operating system (references/metavr-device-management.md).
  • Evidence: The metavr app install command includes a --grant-permissions flag which automatically assigns all requested permissions to an application at install time (references/metavr-app-management.md).
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the dynamic download and execution of the metavr utility from the NPM registry.
  • Evidence: The SKILL.md file recommends the use of npx -y metavr for various operations, which triggers the download of the package from the NPM registry at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 06:57 PM
Security Audit — agent-trust-hub — metavr-cli