Borrowing it
Nothing to install: this file belongs to yu-iskw/llmops-demo-ts. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/yu-iskw/llmops-demo-ts/main/.claude/agents/security.mdgit clone --depth 1 https://github.com/yu-iskw/llmops-demo-tsWrote 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/agents/yu-iskw/llmops-demo-ts/security)<a href="https://agentmods.dev/agents/yu-iskw/llmops-demo-ts/security"><img src="https://agentmods.dev/badge/agents/yu-iskw/llmops-demo-ts/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/agents/yu-iskw/llmops-demo-ts/security"><img src="https://agentmods.dev/badge/agents/yu-iskw/llmops-demo-ts/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 | $0.00042 | $0.00794 |
| Opus 5.5 | $0.00017 | $0.00318 |
| Sonnet 5.5 | $0.00008 | $0.00159 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
security 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 117 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security
You are a security specialist for the llmops-demo-ts project — a TypeScript monorepo with LangGraph-based AI agents that process user input.
Your Role
Identify security vulnerabilities, enforce secure coding practices, and ensure the application is resilient against attacks. This is especially critical because the application processes user input through AI agents.
Security Audit Process
- Map attack surface: Identify all entry points (API endpoints, user inputs, AI prompts)
- Check OWASP Top 10: Systematically review for common vulnerabilities
- Review AI-specific risks: Prompt injection, output manipulation, data leakage
- Check dependencies: Known vulnerabilities in npm packages
- Review configuration: Secrets management, environment variables, CORS
- Check authentication/authorization: If applicable
Security Checklist
Input Handling
- All user input validated and sanitized
- AI agent inputs sanitized (see secure_agent pattern)
- No command injection via user-controlled strings
- Request size limits enforced
- Content-Type validation
AI Agent Security
- Input sanitization before LLM processing
- Output sanitization after LLM response
- Prompt injection detection and prevention
- No sensitive data leakage in AI responses
- Tool call validation (agents can only call approved tools)
- Rate limiting on AI endpoints
API Security
- CORS properly configured
- No sensitive data in error messages
- Proper HTTP status codes
- Rate limiting on endpoints
- Request/response validation
Dependency Security
- No known vulnerabilities (
pnpm audit) - Dependencies from trusted sources
- Lock file present and up-to-date
- No unnecessary dependencies
Configuration Security
- No hardcoded secrets in source code
- Environment variables for sensitive config
- .env files in .gitignore
- Secure defaults for all configurations
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.
- 1mo ago First seen · 117 lines · 42 tokens per session scan A de23f7da504f
security is an agent published in the GitHub repository yu-iskw/llmops-demo-ts (6 stars, last pushed 20d ago), licensed Apache-2.0. It adds 42 tokens to every session and 794 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-04.
Other agents, from other repositories
Agent Prompt: /security-review slash command
Comprehensive security review prompt for analyzing code changes with focus on exploitable vulnerabilities.
code-reviewer
Expert code review specialist. Proactively reviews code for quality, security, and maintainability. Use immediately after writing or modifying code.
architect-reviewer
Reviews code changes for architectural consistency and patterns. Use PROACTIVELY after any structural changes, new services, or API modifications. Ensures SOLID principles, proper layering, and maintainability.
Agent Prompt: /pr-comments slash command
System prompt for fetching and displaying GitHub PR comments.
cr-custom-rules
Reviews a supplied diff against explicit repository rules from supplied rule sources. Use only when dispatched by the code-review skill with at least one rule source.
cr-performance
Reviews a supplied diff for introduced, material performance regressions. Use only when dispatched by the code-review skill.