isolved
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Installs the Membrane CLI tool (@membranehq/cli) from the public npm registry to enable interaction with the Membrane platform.
- [COMMAND_EXECUTION]: Executes shell commands via the membrane CLI to manage connections, search for capabilities, and run HRIS-related actions.
- [PROMPT_INJECTION]: The skill ingests external data from Isolved and uses natural language descriptions for action discovery and creation, presenting a surface for indirect prompt injection. * Ingestion points: Data retrieved from Isolved via membrane action run in SKILL.md. * Boundary markers: Absent; the instructions do not specify delimiters for wrapping external data when processed by the agent. * Capability inventory: Subprocess execution of the membrane CLI tool for connection management and action execution in SKILL.md. * Sanitization: Absent; no explicit validation or filtering of retrieved HRIS data is defined in the instructions.
Audit Metadata