big-cartel

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides the user to install the @membranehq/cli package from NPM, which is the official tool for the Membrane platform provided by the vendor.
  • [COMMAND_EXECUTION]: Utilizes the membrane command-line interface to perform operations such as searching for connectors, establishing connections, and running API actions. This behavior is standard for the skill's intended purpose.
  • [PROMPT_INJECTION]: The skill processes external data from the Big Cartel API (e.g., products and orders). This constitutes an indirect prompt injection surface. Evidence: 1. Ingestion points: Big Cartel API responses (SKILL.md); 2. Boundary markers: Not explicitly defined in the instructions; 3. Capability inventory: Subprocess execution via the membrane CLI tool; 4. Sanitization: No explicit sanitization or validation logic is specified in the prompt instructions. This is a common characteristic of data-integrating skills and does not represent an active threat.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 10:26 AM