bitly

Pass

Audited by Gen Agent Trust Hub on Apr 30, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the installation of the @membranehq/cli package via npm. This is a vendor-owned resource for the 'membranedev' organization and is used for its intended purpose of managing platform integrations.
  • [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it processes data from external sources (Bitly) and provides capabilities to execute actions based on that data.
  • Ingestion points: Data retrieved via membrane action run and membrane action list from the Bitly API.
  • Boundary markers: None specified in the instructions for delimiting external content.
  • Capability inventory: The membrane CLI allows for network operations and action execution through the Membrane platform.
  • Sanitization: No explicit sanitization or validation steps are documented for the external data before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 30, 2026, 03:19 AM