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.
npx skills add 0dayInc/pwn --skill system_prompt_extractiongit clone --depth 1 https://github.com/0dayInc/pwnWrote 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.
[](https://agentmods.dev/skills/0dayinc/pwn/system_prompt_extraction)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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
scansecurity_referencesauthorshelp
References
references/security.md— CWE / NIST mappingreferences/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.
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.
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.
- 7d ago First seen · 54 lines · 28 tokens per session scan A c49ef778bff9
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.
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.
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.
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…
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…
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.
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.