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 MingyiSecLab/Mingyi-Atlas --skill prompt-injectiongit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/prompt-injection)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/prompt-injection"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/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/mingyiseclab/mingyi-atlas/prompt-injection"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/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 | $0.00055 | $0.01344 |
| Opus 5 | $0.00028 | $0.00672 |
| Sonnet 5 | $0.00011 | $0.00269 |
| Haiku 4.5 | $0.00006 | $0.00134 |
Grade A, and why
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 12d 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
98% identical to prompt-injection — 3 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.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Prompt Injection Playbook
Every product shipping an LLM interface in 2026 has this surface. The bug bounty payouts are high because nobody has a clean defense, and the chain impact is unbounded (prompt injection → tool call → exfil → RCE in the agent's sandbox).
1. Target inventory — what counts as an LLM application
- Chatbots with document upload / RAG
- IDE copilots and code-review bots
- Email assistants (classic indirect-injection vector)
- Browser agents / AI-powered scraping tools
- Customer support bots with CRM tool access
- Agentic frameworks (LangChain, CrewAI, Semantic Kernel) running tools
- CI/CD bots that read PR descriptions into a prompt
- Internal "chat with your data" dashboards
2. Injection vectors
Direct
User-controlled chat input reaches the system prompt (or overrides it through role-play: "Ignore previous instructions and...").
Indirect (the real money)
Attacker-controlled content flows through a document the LLM later ingests:
- PDF upload parsed by the LLM
- Email body summarised by an assistant
- Webpage scraped by a browser agent
- Git diff read by a code-review bot
- Slack message that a bot reads on trigger
- RAG corpus poisoning (add a malicious document to the search index)
Tool-description injection
If tools are registered dynamically (plugin marketplace), a malicious plugin can supply a tool description that tricks the model into calling it.
3. Audit workflow
# Find LLM call sites
grep -rE 'openai|anthropic|bedrock|ollama|gemini|litellm' /workspace/src
grep -rE 'ChatOpenAI|ChatAnthropic|LLM\(|create_agent' /workspace/src
# Find prompt templates built from user input
grep -rE '(f"|f\x27|format\()[^"\x27]*\{(user|input|body|message|content|text)' /workspace/src
# Find tool definitions (LangChain @tool decorators, OpenAI tool_spec)
grep -rE '@tool|tools\s*=|function_calling|tool_choice' /workspace/src
For each tool definition, ask:
- Does the tool perform filesystem / network / shell / DB operations?
- What happens if the LLM calls it with attacker-chosen arguments?
- Is there a human-in-the-loop confirmation?
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.
- 12d ago First seen · 138 lines · 55 tokens per session scan E 19a387520867
prompt-injection is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 55 tokens to every session and 1,344 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 98% identical to prompt-injection, differing in 3 lines, and is treated as a copy.
Other skills, from other repositories
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-4.3
Ensure AWS Config is enabled in all regions.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.5
Ensure MFA is enabled for the 'root' user account.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.