pwn-ai-redteam-systempromptextraction

pwn-ai-redteam-systempromptextraction is a skill for Claude Code from 0dayInc/pwn. It costs 28 tokens per session (348 once invoked), scanned A, original, MIT.

An AI security testing module that tries to make a language model reveal its hidden system prompt, developer instructions, or safety settings.

In plain words
What is it for?
Use it to test whether an AI application discloses its private instructions or guardrail configuration.
Why use it?
It helps find information leaks that could expose internal rules and make later attacks easier.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to test whether an AI application discloses its private instructions or guardrail configuration.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/0dayinc/pwn/system_prompt_extraction
View source ↗ 0dayInc/pwn
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 0dayInc/pwn --skill system_prompt_extraction
Clone the repo
git clone --depth 1 https://github.com/0dayInc/pwn

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 pwn-ai-redteam-systempromptextraction

README.md
[![agentmods](https://agentmods.dev/badge/skills/0dayinc/pwn/system_prompt_extraction/github.svg)](https://agentmods.dev/skills/0dayinc/pwn/system_prompt_extraction)
Your own site
<a href="https://agentmods.dev/skills/0dayinc/pwn/system_prompt_extraction"><img src="https://agentmods.dev/badge/skills/0dayinc/pwn/system_prompt_extraction/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 pwn-ai-redteam-systempromptextraction

Your own site · 80×15
<a href="https://agentmods.dev/skills/0dayinc/pwn/system_prompt_extraction"><img src="https://agentmods.dev/badge/skills/0dayinc/pwn/system_prompt_extraction.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 348 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 pass 7 Sept 2026
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 $0.00028 $0.00348
Opus 5 $0.00014 $0.00174
Sonnet 5 $0.00006 $0.00070
Haiku 4.5 $0.00003 $0.00035

Measured 7d ago against content hash c49ef778bff9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

pwn-ai-redteam-systempromptextraction 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.

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.

etc/default_skills/pwn/ai/red_team/system_prompt_extraction/SKILL.md · 54 lines

What it actually says

PWN::AI::RedTeam::SystemPromptExtraction

AI RedTeam Module used to attempt extraction / leakage of the target LLM's hidden system prompt, developer instructions, or guardrail configuration.

When to use

Call PWN::AI::RedTeam::SystemPromptExtraction from pwn_eval when the task needs this module. Do not reimplement it in shell.

Methodologies

Generated from pwn/ai/red_team/system_prompt_extraction.rb. Prefer the public class methods below. Class methods take (opts = {}) and read opts.

How to call

PWN::AI::RedTeam::SystemPromptExtraction.help
PWN::AI::RedTeam::SystemPromptExtraction.scan(opts)

Public methods

  • scan
  • security_references
  • authors
  • help

References

  • references/security.md — CWE / NIST mapping
  • references/urls.md — URLs from source

Source

pwn/ai/red_team/system_prompt_extraction.rb

Verification

PWN::AI::RedTeam::SystemPromptExtraction.respond_to?(:scan) after the module is loaded. Read the source for parameter names.

Files

What ships with it

2 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 · 54 lines · 28 tokens per session scan A c49ef778bff9

Subscribe to this mod's changes

pwn-ai-redteam-systempromptextraction is a skill published in the GitHub repository 0dayInc/pwn (81 stars, last pushed today), licensed MIT. It adds 28 tokens to every session and 348 once invoked, about $0.0001 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

claude-code-prompt

Reference Claude Code's prompt engineering patterns for AI/Agent development. Provides best practices for system prompts, tool design, agent orchestration, and safety.

xiufengsun/claude-code-prompt · 36 tokens

seedance-vocab-en

This skill should be used when an English Seedance 2.0 prompt needs clearer production wording, less generic prose, or precise vocabulary for camera, lighting, motion, VFX, audio, and constraints. Route blocked prompts through seedance-filter for context and boundary review.

Emily2040/seedance-2.0 · 61 tokens

ssti

Server-Side Template Injection — fingerprint the engine first (Jinja2 / Twig / Velocity / Freemarker / ERB / Smarty / Mako / Handlebars / Pug), then escalate the engine-specific primitive to RCE or sandbox escape. Use when user input is reflected through a template engine…

PentesterFlow/agent · 99 tokens

llm-router

Selects the optimal LLM model and provider for each task based on complexity, cost budget, and capability requirements. Routes cheap tasks to Haiku/GPT-4o-mini and complex tasks to Sonnet/Opus/o1. Use when deciding which model to call, optimizing LLM costs, or building multi-model agent systems. Activate on "which…

curiositech/some_claude_skills · 121 tokens

opik-optimizer

Optimize LLM prompts, tools, and agents in Opik using standardized optimizer workflows (prompt optimization, tool optimization, and parameter tuning), dataset/metric wiring, and result interpretation.

vincentkoc/dotskills · 41 tokens

prompt-optimizer

A prompt-writing assistant that turns a rough request into a clearer set of instructions for an AI system. It can adapt the wording and format for services such as Claude, ChatGPT, Gemini, and other named platforms.

TestAny-io/testany-agent-skills · 62 tokens