raisely

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the @membranehq/cli package from the npm registry. This is the official command-line tool for the Membrane platform, used to facilitate the integration.
  • [COMMAND_EXECUTION]: The skill relies on executing membrane CLI commands to authenticate, connect to Raisely, and execute actions. These operations are standard for using the Membrane integration framework.
  • [PROMPT_INJECTION]: The skill accepts natural language strings for action discovery and JSON objects for action parameters. This represents an indirect prompt injection surface where user-provided input is interpolated into command arguments.
  • Ingestion points: User-provided intent queries in membrane action list and input payloads in membrane action run (SKILL.md).
  • Boundary markers: Not used for command arguments.
  • Capability inventory: The skill utilizes a CLI capable of making network requests and managing remote integration logic.
  • Sanitization: Not explicitly defined within the skill instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 10:20 PM
Security Audit — agent-trust-hub — raisely