breezy
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill recommends installing the Membrane CLI (
@membranehq/cli) via npm. This is a well-known tool from the skill's author ('membranedev') and is used for its intended purpose of managing API connections and actions.\n- [COMMAND_EXECUTION]: The skill provides variousmembraneCLI commands for the agent to use (e.g.,membrane login,membrane action run). These are standard operational commands for the Membrane ecosystem and do not involve unauthorized privilege escalation or persistence mechanisms.\n- [DATA_EXFILTRATION]: No evidence of sensitive data exfiltration. The skill uses a secure proxy (membrane request) that manages authentication tokens server-side, preventing exposure of API keys or credentials in the local environment or logs.\n- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it retrieves data from Breezy HR (candidates, notes, etc.). However, it follows best practices by using structured CLI outputs and recommended boundary markers for managing external content.
Audit Metadata