filestack

Pass

Audited by Gen Agent Trust Hub on Apr 26, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the Membrane CLI tool (@membranehq/cli) from the official npm registry. This is a standard utility provided by the vendor for interacting with their platform.
  • [COMMAND_EXECUTION]: Uses the membrane command-line utility to perform operations such as searching for connectors, managing connections, and executing FileStack actions. All commands are scoped to the user's Membrane tenant.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection because it processes data (content, metadata) from an external source (FileStack).
  • Ingestion points: Untrusted data enters the context via membrane action run and membrane request outputs (SKILL.md).
  • Boundary markers: The skill does not define specific delimiters for separating FileStack data from agent instructions.
  • Capability inventory: The skill can execute CLI commands, run platform actions, and perform HTTP requests to the FileStack API.
  • Sanitization: No explicit sanitization or validation of the retrieved FileStack data is performed before it is presented to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 26, 2026, 06:50 PM