orchestrating-llm-attacks-with-pyrit

orchestrating-llm-attacks-with-pyrit is a skill for Claude Code, Codex from adriannoes/awesome-agentic-ai. It costs 56 tokens per session (2,603 once invoked), scanned A, original, MIT.

A workflow for using Microsoft PyRIT to test conversational AI systems with repeated adversarial conversations. It uses attacker and scorer models to probe a target toward a defined outcome, such as revealing a system prompt or making an unauthorized tool call.

In plain words
What is it for?
Use it to run multi-turn red-team tests against AI models and agents, evaluate restricted-content safeguards, test prompt-leakage risks, and check tool-use boundaries.
Why use it?
Single prompts can miss weaknesses that appear only after several turns. This helps authorized security testers examine how an AI system responds to sustained manipulation attempts.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to run multi-turn red-team tests against AI models and agents, evaluate restricted-content safeguards, test prompt-leakage risks, and check tool-use boundaries.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/adriannoes/awesome-agentic-ai/orchestrating-llm-attacks-with-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 adriannoes/awesome-agentic-ai --skill orchestrating-llm-attacks-with-pyrit
Clone the repo
git clone --depth 1 https://github.com/adriannoes/awesome-agentic-ai

Made for: Claude Code, Codex.

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 orchestrating-llm-attacks-with-pyrit

README.md
[![agentmods](https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/orchestrating-llm-attacks-with-pyrit/github.svg)](https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/orchestrating-llm-attacks-with-pyrit)
Your own site
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/orchestrating-llm-attacks-with-pyrit"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/orchestrating-llm-attacks-with-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 orchestrating-llm-attacks-with-pyrit

Your own site · 80×15
<a href="https://agentmods.dev/skills/adriannoes/awesome-agentic-ai/orchestrating-llm-attacks-with-pyrit"><img src="https://agentmods.dev/badge/skills/adriannoes/awesome-agentic-ai/orchestrating-llm-attacks-with-pyrit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,603 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 2 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high YARA Match · line 2
    YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).
    Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
  • medium Data Exfiltration · line 95
    Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
    Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
How audits are shown
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 $0.00056 $0.02603
Opus 5 $0.00028 $0.01301
Sonnet 5 $0.00011 $0.00521
Haiku 4.5 $0.00006 $0.00260

Measured 7d ago against content hash 16212f596b6d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

orchestrating-llm-attacks-with-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 7d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/agent.py), 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.

cursor-claude-codex/skills/anthropic-cybersecurity-skills/skills/orchestrating-llm-attacks-with-pyrit/SKILL.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Orchestrating LLM Attacks with PyRIT

Legal and Authorized-Use Notice: PyRIT generates adversarial and potentially harmful prompts to test AI systems. Use it only against models and endpoints you own or are explicitly authorized to assess. Multi-turn orchestrators consume large numbers of tokens against both the target and the adversarial/scoring models; account for cost and terms of service. Unauthorized use is prohibited.

Overview

PyRIT (Python Risk Identification Tool for generative AI) is an open-source automation framework from Microsoft's AI Red Team, distributed at github.com/microsoft/PyRIT. Where a single-shot scanner sends one prompt and checks the answer, PyRIT automates multi-turn adversarial conversations: an attacker model and a scorer model collaborate in a loop to drive a target model toward a defined objective (for example, eliciting restricted content, leaking a system prompt, or making an agent perform an unauthorized tool call). This mirrors how real adversaries iterate against a chatbot rather than relying on one magic prompt.

PyRIT is built from composable primitives. Targets (pyrit.prompt_target) wrap the systems being probed and the helper models — OpenAIChatTarget, AzureMLChatTarget, HTTPTarget, and others. Orchestrators / attacks (pyrit.orchestrator) implement attack strategies; all multi-turn strategies subclass MultiTurnOrchestrator. The headline strategies are RedTeamingOrchestrator (a generic adversarial-chat loop), CrescendoOrchestrator (the Crescendo technique — start benign and escalate gradually so each turn looks reasonable in isolation), and TreeOfAttacksWithPruningOrchestrator (TAP — branch multiple attack lines in parallel, expand the branches the scorer rates as progressing, and prune dead ends). Scorers (pyrit.score) such as SelfAskTrueFalseScorer decide whether the objective was met and feed that judgment back into the loop. Converters mutate prompts (base64, translation, ASCII art) to evade filters, and memory persists every turn for later analysis.

Read the full file on GitHub · 226 lines

Files

What ships with it

4 files 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. 7d ago First seen · 226 lines · 56 tokens per session scan A 16212f596b6d

Subscribe to this mod's changes

orchestrating-llm-attacks-with-pyrit is a skill published in the GitHub repository adriannoes/awesome-agentic-ai (57 stars, last pushed 13d ago), licensed MIT. It adds 56 tokens to every session and 2,603 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

agent-safety

Use when bounding an LLM agent that already runs — scoping its task domain, gating tools to least privilege, defending against prompt injection in untrusted web/email/RAG text, requiring human approval on irreversible actions, capping runtime and cost, or triaging what it already did. NOT building the loop, tools, or…

ericrisco/rsc-harness · 79 tokens

llm-prompt-injection

Use when testing an authorized LLM application for prompt injection, system-prompt exposure, unsafe tool use, or RAG data-boundary failures.

uphiago/recon-skills · 36 tokens

opfor-run

Run red-team attacks and generate a report for an agent target.

KeyValueSoftwareSystems/agent-opfor · 17 tokens

opfor-setup

Set up an agent or chatbot target for Opfor red-teaming.

KeyValueSoftwareSystems/agent-opfor · 19 tokens

ai-security-review

Activate when the user asks to audit, review, scan, or assess the security of an AI application, agent, chatbot, or LLM-powered system. Also activate when the user mentions prompt injection, data exfiltration, guardrail bypass, red-teaming, AI SBOM, cognitive policy, OWASP LLM Top 10, NIST AI RMF, or EU AI Act…

NuGuardAI/nuguard · 84 tokens

sbom-analysis

Activate when the user opens, mentions, or asks questions about a .sbom.json file, an AI Bill of Materials, an aibom.json, or asks about what AI components an application uses. Also activate when the user asks about component dependencies, LLM model usage, tool permissions, datastore access, or the attack surface of…

NuGuardAI/nuguard · 75 tokens