surveycto

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill directs users to install the @membranehq/cli package from npm, which is the official command-line interface for the Membrane platform.
  • [COMMAND_EXECUTION]: The instructions make extensive use of the membrane CLI to manage connections, discover actions, and interact with the SurveyCTO API.
  • [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it retrieves and processes survey forms and datasets which could contain untrusted content.
  • Ingestion points: External data enters the agent context through membrane action run and membrane request commands.
  • Boundary markers: The instructions do not specify any markers or delimiters to isolate processed survey data from the agent's internal instructions.
  • Capability inventory: The skill uses the Membrane CLI which has capabilities for network communication and data manipulation.
  • Sanitization: No sanitization or validation of the retrieved survey data is mentioned in the skill documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 09:05 AM