competition-prompt-injection

competition-prompt-injection is a skill for Codex from Asaiuta/reverse-workbench-skill. It costs 105 tokens per session (505 once invoked), scanned A, a copy of competition-prompt-injection, MIT.

A specialised guide for testing prompt-injection and related trust-boundary attacks in an agent system. It is used after the CTF sandbox orchestrator has set up the challenge environment.

In plain words
What is it for?
Use it to investigate retrieval poisoning, memory contamination, planner drift, unsafe tool use, and attempts to make an agent reveal data in capture-the-flag sandbox challenges.
Why use it?
It helps trace how untrusted text can move from retrieved content, memory, or messages into an agent’s plans, tool calls, file paths, network targets, or secret requests.

Skill for Codex

Written for Codex: agents/openai.yaml present. Also seen: $skill-name invocation.

Good fit Use it to investigate retrieval poisoning, memory contamination, planner drift, unsafe tool use, and attempts to make an agent reveal data in capture-the-flag sandbox challenges.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/asaiuta/reverse-workbench-skill/competition-prompt-injection
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 Asaiuta/reverse-workbench-skill --skill competition-prompt-injection
Clone the repo
git clone --depth 1 https://github.com/Asaiuta/reverse-workbench-skill

Made for: 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 competition-prompt-injection

README.md
[![agentmods](https://agentmods.dev/badge/skills/asaiuta/reverse-workbench-skill/competition-prompt-injection/github.svg)](https://agentmods.dev/skills/asaiuta/reverse-workbench-skill/competition-prompt-injection)
Your own site
<a href="https://agentmods.dev/skills/asaiuta/reverse-workbench-skill/competition-prompt-injection"><img src="https://agentmods.dev/badge/skills/asaiuta/reverse-workbench-skill/competition-prompt-injection/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 competition-prompt-injection

Your own site · 80×15
<a href="https://agentmods.dev/skills/asaiuta/reverse-workbench-skill/competition-prompt-injection"><img src="https://agentmods.dev/badge/skills/asaiuta/reverse-workbench-skill/competition-prompt-injection.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 105 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 505 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 100% copy Near-identical to another mod 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 $0.00105 $0.00505
Opus 5 $0.00053 $0.00253
Sonnet 5 $0.00021 $0.00101
Haiku 4.5 $0.00011 $0.00051

Measured 9d ago against content hash 7c0344fa94d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

competition-prompt-injection 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 9d 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.

Origin

This is a copy

100% identical to competition-prompt-injection — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

CTF-Sandbox-Orchestrator/competition-prompt-injection/SKILL.md · 50 lines

What it actually says

Competition Prompt Injection

Use this skill only as a downstream specialization after $ctf-sandbox-orchestrator is already active and has established sandbox assumptions, node ownership, and evidence priorities. If that has not happened yet, return to $ctf-sandbox-orchestrator first.

Use this skill when the challenge is primarily about trust boundaries inside an agentic system.

Reply in Simplified Chinese unless the user explicitly requests English.

Quick Start

  1. Identify the first untrusted content that becomes model-visible.
  2. Map the chain from retrieval, memory, or transcript into planner or executor behavior.
  3. Record the exact point where text becomes a tool argument, file path, network target, or secret request.
  4. Prove one minimal exploit chain before exploring variants.
  5. Keep prompt snippets and tool transitions in compact evidence blocks.

Workflow

1. Map The Control Stack

  • Track system, developer, user, retrieved, memory, planner, and tool-response layers separately.
  • Distinguish claimed capability from runtime-exposed capability.
  • Note what the model can actually call, read, or mutate.

2. Prove The Boundary Crossing

  • Reproduce one chain from untrusted text to changed planner behavior, changed tool args, or secret exposure.
  • Keep the decisive transcript compact: source chunk, rewritten planner state, final tool invocation.
  • Prefer the smallest transcript that still demonstrates the bug.

3. Report By Boundary

  • State which layer failed: retrieval, summarizer, planner, executor, tool normalization, or output post-processing.
  • Separate instruction drift from actual side effect.

Read This Reference

  • Load references/prompt-injection.md for the checklist, evidence layout, and common prompt-boundary pitfalls.

What To Preserve

  • Original malicious chunk or prompt
  • Intermediate summary or planner drift if it matters
  • Final tool args, file paths, or exposed secret surface
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. 9d ago First seen · 50 lines · 105 tokens per session scan A 7c0344fa94d3

Subscribe to this mod's changes

competition-prompt-injection is a skill published in the GitHub repository Asaiuta/reverse-workbench-skill (2 stars, last pushed 26d ago), licensed MIT. It adds 105 tokens to every session and 505 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to competition-prompt-injection, differing in 0 lines, and is treated as a copy.