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 Samurai-goose/SPECTER-The-Illusive-Security-Protocol --skill llm-and-ai-securitygit clone --depth 1 https://github.com/Samurai-goose/SPECTER-The-Illusive-Security-ProtocolWrote 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/samurai-goose/specter-the-illusive-security-protocol/llm-and-ai-security)<a href="https://agentmods.dev/skills/samurai-goose/specter-the-illusive-security-protocol/llm-and-ai-security"><img src="https://agentmods.dev/badge/skills/samurai-goose/specter-the-illusive-security-protocol/llm-and-ai-security/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/samurai-goose/specter-the-illusive-security-protocol/llm-and-ai-security"><img src="https://agentmods.dev/badge/skills/samurai-goose/specter-the-illusive-security-protocol/llm-and-ai-security.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 | $0.00064 | $0.03288 |
| Opus 5 | $0.00032 | $0.01644 |
| Sonnet 5 | $0.00013 | $0.00658 |
| Haiku 4.5 | $0.00006 | $0.00329 |
Grade B, and why
llm-and-ai-security scanned grade B with 1 finding 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.
Instruction-override phrasingmediumPrompt injection
Text telling the model to disregard its earlier instructions or safety rules is the shape of a prompt injection, whoever wrote it.
- [ ] Test role-play escape: "Ignore all previous instructions and..." Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 269 lines — stays where its author put it; the contents beside it link to each section on GitHub.
LLM & AI Security Assessment
Purpose
Test the security and safety posture of systems that embed, expose, or rely on large language models and other AI/ML components. AI introduces an entirely new class of attack vectors beyond traditional web vulnerabilities: adversarial inputs that manipulate model behavior, data leakage through inference, agentic systems that execute actions on behalf of the model, and safety failures that cause harm or legal exposure. This skill applies the OWASP LLM Top 10 (2025) and AI red teaming methodology to assess AI-integrated targets.
Triggers
- Target application uses an LLM (ChatGPT, Claude, Gemini, open-source models)
- AI chatbot, copilot, or assistant interface discovered during recon
- AI agents or agentic workflows in scope (tools, plugins, function-calling)
- Text-to-image, code generation, or other GenAI features in scope
- AI red teaming exercise requested
- Recon identifies AI API endpoints (OpenAI, Anthropic, Cohere, Mistral, etc.)
- Mobile/web app with conversational AI interface
- AI model deployed behind internal API
Required Inputs
| Input | Description | Required |
|---|---|---|
governance_context |
Active engagement governance record | Yes |
ai_target |
Application, API endpoint, or model interface | Yes |
ai_type |
LLM chatbot / AI agent / GenAI feature / fine-tuned model | Auto-detected |
model_info |
Model provider and name if known (GPT-4, Claude, Gemini, etc.) | Recommended |
system_prompt |
System prompt if accessible or inferable | Recommended |
integration_context |
What tools/APIs the AI can access (RAG, web, code exec, email, etc.) | Recommended |
source_code |
Application code calling the AI API | Recommended |
AI Safety vs AI Security
Before testing, classify the scope:
| Domain | Focus | Risk Profile |
|---|---|---|
| AI Security | Protecting the AI system from external threats | Confidentiality, Integrity, Availability of the system the AI is embedded in |
| AI Safety | Protecting the world from the AI system | Harmful content generation, policy violations, unintended behavior, bias |
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 · 269 lines · 64 tokens per session scan B 1eee2b07336a
llm-and-ai-security is a skill published in the GitHub repository Samurai-goose/SPECTER-The-Illusive-Security-Protocol (2 stars, last pushed 2mo ago), licensed MIT. It adds 64 tokens to every session and 3,288 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 1 finding (instruction-override phrasing). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…