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 Asaiuta/reverse-workbench-skill --skill competition-prompt-injectiongit clone --depth 1 https://github.com/Asaiuta/reverse-workbench-skillWrote 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/asaiuta/reverse-workbench-skill/competition-prompt-injection)<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.
<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>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 | $0.00105 | $0.00505 |
| Opus 5 | $0.00053 | $0.00253 |
| Sonnet 5 | $0.00021 | $0.00101 |
| Haiku 4.5 | $0.00011 | $0.00051 |
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.
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.
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
- Identify the first untrusted content that becomes model-visible.
- Map the chain from retrieval, memory, or transcript into planner or executor behavior.
- Record the exact point where text becomes a tool argument, file path, network target, or secret request.
- Prove one minimal exploit chain before exploring variants.
- 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.mdfor 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
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.
- 9d ago First seen · 50 lines · 105 tokens per session scan A 7c0344fa94d3
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.
Other skills, from other repositories
osint-recon
A knowledge guide for open-source intelligence, or OSINT: collecting information from publicly available sources. It covers servers, websites, domains, and, when appropriate, people.
hackerone
A safety wrapper for HackerOne bug-bounty testing that reads a program's allowed targets and rules before handing each allowed asset to a penetration-testing workflow. HackerOne is a platform where companies invite researchers to report security bugs.
crypto-toolkit
A toolkit for encoding, decoding, hashing, and encrypting data in formats such as Base64, hexadecimal, URLs, JWTs, AES, RSA, and common ciphers.
redteam-cve-lookup
CVE lookup and applicability assessment domain card. Use after reconnaissance has identified products, versions, services, or fingerprints and red-team mode needs evidence-based CVE matching before deeper testing.
redteam-cve-validation
CVE validation domain card. Use after CVE lookup has produced applicable or candidate CVEs and red-team mode needs scoped evidence to decide whether to continue, pivot, or report.
secknowledge-skill
A knowledge base for testing the security of websites, software, and AI systems, including agents and language models.