actian

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes steps to install the @membranehq/cli package from NPM, which is a vendor-owned resource for the integration service.
  • [COMMAND_EXECUTION]: The skill utilizes several membrane CLI commands for authentication, connection management, and running database actions.
  • [PROMPT_INJECTION]: The skill processes data from external Actian database actions, presenting a surface for indirect prompt injection. Ingestion points: Output from database actions in SKILL.md. Boundary markers: No specific delimiters defined. Capability inventory: Use of Membrane CLI for network and data operations. Sanitization: No explicit sanitization of external content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 06:29 AM