er-diagram

Pass

Audited by Gen Agent Trust Hub on Jul 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Security analysis of the skill's instructions and provided scripts reveals no evidence of malicious behavior, data exfiltration, or safety bypasses. The skill operates exclusively within the user's local environment to interface with a specific desktop application.- [COMMAND_EXECUTION]: The skill employs local shell scripts (scripts/new-canvas and scripts/tq) to manage the creation of .tldraw files and to send requests to the application's local API. These scripts utilize common tools such as curl, python3, and open for their intended integration tasks.- [EXTERNAL_DOWNLOADS]: The documentation provides links to offline.tldraw.com for users to install the tldraw desktop application, which is a well-known service.
  • [DATA_EXFILTRATION]: The skill reads a local configuration file (server.json) to obtain the port and per-launch authorization token necessary for communicating with the local tldraw server. This information is strictly used for requests to localhost.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 26, 2026, 05:42 PM
Security Audit — agent-trust-hub — er-diagram