onespan

Pass

Audited by Gen Agent Trust Hub on Apr 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the official @membranehq/cli from the npm registry to support platform integration.
  • [COMMAND_EXECUTION]: Uses the membrane CLI to execute actions and manage connections, which is the documented method for interacting with the platform.
  • [SAFE]: The skill follows security best practices by delegating authentication to the Membrane platform, preventing local credential exposure.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection via data ingested from the OneSpan API. Evidence: 1. Ingestion: Output from membrane action run and membrane request. 2. Boundary markers: Absent. 3. Capability inventory: Network access via membrane request. 4. Sanitization: Absent. The risk is assessed as safe/low given the intended use of structured actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 29, 2026, 12:59 AM
Security Audit — agent-trust-hub — onespan