knack

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill installs the @membranehq/cli package via npm, which is the official command-line interface for the Membrane platform.
  • [COMMAND_EXECUTION]: Employs the membrane CLI tool to manage Knack connections and execute actions. This is the primary method of interaction and is used according to the vendor's specifications.
  • [PROMPT_INJECTION]: Indirect prompt injection risk analysis: Ingestion points: Knack record data accessed via get-record, list-records, and request commands in SKILL.md. Boundary markers: None present. Capability inventory: Command execution via membrane action run and membrane request in SKILL.md. Sanitization: None explicitly defined. This is a standard data ingestion surface for this type of integration and no malicious content or bypass attempts were detected.
  • [SAFE]: No evidence of malicious behavior, obfuscation, or unauthorized data access was found. Authentication and credential management are securely handled by the Membrane platform.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 04:24 PM