datasette

Pass

Audited by Gen Agent Trust Hub on Jun 21, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides instructions for interacting with an internal organizational service at http://analytics/. It is designed for internal data exploration and retrieval tasks, using network-level access controls rather than hardcoded credentials.
  • [COMMAND_EXECUTION]: Utilizes curl and jq for API interaction and response processing. The commands are well-defined for data retrieval and do not include patterns for shell injection or unauthorized system modification.
  • [EXTERNAL_DOWNLOADS]: References a JSON schema hosted on https://files.ourworldindata.org. This is a trusted domain belonging to the skill author (OWID) used for legitimate configuration reference.
  • [DATA_EXFILTRATION]: Network operations are limited to the organization's internal endpoint and official domain. There are no instructions for accessing sensitive local files or transmitting user data to unauthorized third-party services.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 21, 2026, 07:11 AM
Security Audit — agent-trust-hub — datasette