generate-synthetic-dataset

Pass

Audited by Gen Agent Trust Hub on Apr 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is authored by orq-ai and all external interactions are confined to the vendor's official domains (orq.ai).
  • [SAFE]: Secure credential management is encouraged by instructing the use of environment variables ($ORQ_API_KEY) for API authentication rather than hardcoding secrets.
  • [SAFE]: The skill includes strong safety constraints that require explicit user confirmation for all destructive actions, such as deleting or modifying existing datapoints.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill reads and writes dataset content using the orq.ai API. These operations are essential to the skill's core functionality and target the vendor's own infrastructure, posing no unauthorized exfiltration risk.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect injection surface as it ingests untrusted data from existing datasets via the list_datapoints tool and HTTP GET requests. However, the risk is mitigated by explicit instructions for human review of all generated content and mandatory confirmation for modifications. Capabilities include the ability to create, update, and delete datapoints within the platform's environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 10, 2026, 07:38 AM