next-bulk-fulfill

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill generates a Python script locally and executes it using the Bash tool to perform bulk API requests. This is a standard automation pattern but involves dynamic script generation and execution.
  • [EXTERNAL_DOWNLOADS]: The skill performs network requests to *.29next.store and api.admin endpoints to validate credentials and process fulfillment data. These operations target the vendor's official infrastructure.
  • [DATA_EXPOSURE]: The skill requests an API key from the user. While this involves handling credentials, the instructions specify using a restricted key for specific platform scopes and communicate only with official endpoints.
  • [PROMPT_INJECTION]: The skill identifies an attack surface for indirect prompt injection as it ingests and processes user-provided CSV files. It includes validation steps and dry-run modes to mitigate errors during data processing.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 11:43 PM
Security Audit — agent-trust-hub — next-bulk-fulfill