Skills
skills/igmarin/elixir-phoenix-skills/review-model-performance/Gen Agent Trust Hub

review-model-performance

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Uses standard shell commands like find and ls to identify project configuration files (tile.json) and evaluation scenarios.
  • [COMMAND_EXECUTION]: Orchestrates the tessl CLI to manage authentication (tessl whoami), generate test scenarios, and execute model comparison jobs.
  • [EXTERNAL_DOWNLOADS]: Interacts with remote services via the CLI (tessl scenario download, tessl eval run) and provides monitoring links to the tessl.io dashboard.
  • [EXTERNAL_DOWNLOADS]: Suggests expanding functionality by installing the tessl-labs/eval-improve skill from the platform's official labs repository.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 03:13 AM
Security Audit — agent-trust-hub — review-model-performance