peoplehr

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package via npm. This is the official command-line interface provided by the platform vendor for interacting with their services.
  • [COMMAND_EXECUTION]: The instructions utilize the membrane CLI to perform various tasks including authentication, connection management, and running PeopleHR actions.
  • [SAFE]: The skill explicitly promotes the use of managed connections, instructing that the agent should never ask for or store raw API keys or tokens locally.
  • [SAFE]: Data ingestion surface (Indirect Prompt Injection): 1. Ingestion points: External HR data is ingested through membrane action run and membrane request commands in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: The skill uses the membrane CLI for network operations and data retrieval. 4. Sanitization: Not specified. The reliance on the platform's structured actions and proxy provides a mitigated environment for processing external data.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 09:05 PM