mockaroo

Pass

Audited by Gen Agent Trust Hub on Apr 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Downloads the Membrane CLI from the public NPM registry. This package is maintained by the skill's author and is required for the integration.
  • [COMMAND_EXECUTION]: Uses the membrane command-line tool to manage connections, list actions, and execute integration logic. This includes the dynamic creation of new actions based on user descriptions.
  • [DATA_EXFILTRATION]: Facilitates data exchange with the Mockaroo service. The skill instructions prioritize security by offloading authentication and credential storage to the Membrane platform.
  • [PROMPT_INJECTION]: Ingests external data from the Mockaroo API, creating a surface for potential indirect prompt injection. Ingestion points: Output from the membrane action run command. Boundary markers: Delimiters or ignore-instructions for the agent are not specified in the skill content. Capability inventory: Subprocess execution and network access via the vendor's CLI. Sanitization: No explicit sanitization or validation of the retrieved external content is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 28, 2026, 04:46 PM
Security Audit — agent-trust-hub — mockaroo