prestashop

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Installs the official @membranehq/cli from the NPM registry, which is the designated tool for this skill's functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill enables the agent to search for actions using natural language intents, creating a potential surface for indirect instructions.
  • Ingestion points: The intent argument in the membrane action list command (SKILL.md).
  • Boundary markers: None explicitly defined in the prompt instructions.
  • Capability inventory: The skill can list, create, and execute actions via the CLI (SKILL.md).
  • Sanitization: Security is enforced server-side through the vendor's platform architecture.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 09:39 AM