mozilla-observatory

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides the user to install the @membranehq/cli package from the npm registry. This is the official command-line interface provided by the vendor (membranedev) for interacting with their infrastructure.
  • [COMMAND_EXECUTION]: The instructions involve executing various subcommands of the membrane CLI, such as login, connect, and action run. These are standard operational commands for the intended functionality of the skill.
  • [DATA_EXFILTRATION]: The skill promotes secure credential management by using the Membrane platform's native connection system. It explicitly advises against asking users for API keys or tokens, instead delegating authentication lifecycle management to the platform's server-side logic.
  • [REMOTE_CODE_EXECUTION]: While the skill mentions membrane action create which triggers the generation of new logic on the Membrane platform, this is a core feature of the managed service rather than an arbitrary or hidden remote execution vulnerability within the skill's own instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 10:49 PM