PyRIT

PyRIT is a skill for Claude Code from CarbeneAI/Forge. It costs 109 tokens per session (1,422 once invoked), scanned A, original, MIT.

An AI security testing framework for checking language models and generative AI systems for jailbreaks, prompt injection, harmful responses, data leaks, and multi-step attacks.

In plain words
What is it for?
Use it to test hosted or local AI models, web-based AI apps, and custom endpoints with attack prompts, datasets, and scoring methods.
Why use it?
It helps teams find safety and security weaknesses before attackers or users encounter them. It also supports evidence gathering for AI risk and governance assessments.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

Good fit Use it to test hosted or local AI models, web-based AI apps, and custom endpoints with attack prompts, datasets, and scoring methods.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/carbeneai/forge/pyrit
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add CarbeneAI/Forge --skill pyrit
Clone the repo
git clone --depth 1 https://github.com/CarbeneAI/Forge

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for PyRIT

README.md
[![agentmods](https://agentmods.dev/badge/skills/carbeneai/forge/pyrit/github.svg)](https://agentmods.dev/skills/carbeneai/forge/pyrit)
Your own site
<a href="https://agentmods.dev/skills/carbeneai/forge/pyrit"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/pyrit/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for PyRIT

Your own site · 80×15
<a href="https://agentmods.dev/skills/carbeneai/forge/pyrit"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/pyrit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,422 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.01422
Opus 5 $0.00055 $0.00711
Sonnet 5 $0.00022 $0.00284
Haiku 4.5 $0.00011 $0.00142

Measured 6d ago against content hash 71e91f6e08d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

PyRIT scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 6d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (tools/run-pyrit.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/PyRIT/SKILL.md · 117 lines

How it starts

The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PyRIT — AI Red-Teaming Framework

Microsoft AI Red Team's open-source framework for proactively identifying risks in generative AI systems. Used here for offensive AI engagements (Ehud) and AI governance testing evidence (Daniel CCO — NIST AI RMF MEASURE function, ISO 42001 testing requirements).

Authorized Use Only

PyRIT is for testing AI systems you own or have explicit written permission to test. Engagement scope MUST be defined before running any attack orchestrator. Generated harmful content stays inside the engagement memory store and is purged after report delivery.

Capabilities

  • Single-turn attacks — direct prompts, converters (Base64, ROT13, leetspeak, translation, role-play wrappers, etc.)
  • Multi-turn attacks — Crescendo, TAP (Tree of Attacks with Pruning), Skeleton Key, custom orchestrators
  • Targets — Anthropic Claude, OpenAI, Azure OpenAI, Google, HuggingFace, Ollama (local), custom HTTP/WebSocket endpoints, Playwright-driven web apps
  • Scorers — true/false, Likert, classification, Azure AI Content Safety, custom LLM-as-judge
  • Datasets — content harms, psychosocial risks, data leakage, prompt injection corpora
  • Memory — SQLite (default) for engagement audit trail; Azure SQL optional
  • CLIpyrit_scan (automated), pyrit_shell (interactive)

Workflow Routing

Action Trigger Behavior
Quick Scan "AI red team scan", "test this LLM" Run pyrit_scan with default scenarios against target
Jailbreak Test "jailbreak test", "test guardrails" Crescendo or Skeleton Key orchestrator
Prompt Injection "prompt injection test", "test for injection" Single-turn injection corpus + scorer
Multi-turn TAP "tree of attacks", "TAP attack", "deep red team" TAP orchestrator with adversarial LLM
Custom Engagement "custom AI red team", "build PyRIT scenario" Drop into Python with tools/run-pyrit.sh
Governance Evidence "AI risk assessment", "NIST AI RMF MEASURE", "ISO 42001 testing" Run scoped scan, output to Obsidian for audit binder

Read the full file on GitHub · 117 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 6d ago First seen · 117 lines · 109 tokens per session scan A 71e91f6e08d2

Subscribe to this mod's changes

PyRIT is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,422 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.