# Probe ML and LLM systems for regressions and vulnerabilities with Giskard

> Run automated red-team and failure scans against an LLM or RAG app before users find the breakage.

- Skill: `agentskillexchange/probe-ml-and-llm-systems-for-regressions-and-vulnerabilities` (Agent Skill)
- Install (CLI): `npx skillmds@latest add agentskillexchange/probe-ml-and-llm-systems-for-regressions-and-vulnerabilities`
- Raw SKILL.md: https://api.skillmd.com/api/skills/agentskillexchange/probe-ml-and-llm-systems-for-regressions-and-vulnerabilities/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: agentskillexchange (https://skillmd.com/u/agentskillexchange)
- Updated: 2026-09-08
- Page: https://skillmd.com/skills/agentskillexchange/probe-ml-and-llm-systems-for-regressions-and-vulnerabilities

---


# Probe ML and LLM systems for regressions and vulnerabilities with Giskard

Run automated red-team and failure scans against an LLM or RAG app before users find the breakage.

## Prerequisites

Python environment, Giskard open-source package, model or RAG application access, test datasets or prompts, model provider credentials where required

## Installation

Use the upstream install or setup path that matches your environment:
- pip install giskard

Requirements and caveats from upstream:
- Requires Python 3.12+.

Basic usage or getting-started notes:
- sh
- **Telemetry:** Libraries built on giskard-core (including giskard-checks) may send **optional, aggregated usage analytics** to help improve the product. No prompts, model outputs, or scenario text are included. See [w...

- Source: https://github.com/Giskard-AI/giskard-oss
- Extracted from upstream docs: https://raw.githubusercontent.com/Giskard-AI/giskard-oss/HEAD/README.md

## Documentation

- https://docs.giskard.ai/

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/probe-ml-and-llm-systems-for-regressions-and-vulnerabilities-with-giskard/)