skills/keboola/ai-kit/mcp-data-app/Gen Agent Trust Hub

mcp-data-app

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements robust security practices, including the use of Bearer authentication with timing-attack resistant comparisons (hmac.compare_digest) in the server implementation.
  • [EXTERNAL_DOWNLOADS]: Fetches dependencies from official GitHub repositories belonging to the vendor (Keboola) and well-known public registries (PyPI, NPM). These are documented as part of the standard build and deployment process.
  • [COMMAND_EXECUTION]: Provides a local scaffolding script (scripts/scaffold.sh) to initialize project directories. The script performs standard file copying and permission settings without involving untrusted input or elevated privileges.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 08:48 AM