ai-security-engineer

ai-security-engineer is an agent for Claude Code from Kaademos/secure-sdlc-agents. It costs 195 tokens per session (2,143 once invoked), scanned B, original, MIT.

A specialist guide for securing applications that use AI or language models. It covers risks such as prompt injection, unsafe model output, excessive permissions, data leaks, and compromised training or retrieval data.

In plain words
What is it for?
It is for assessing AI features against the OWASP Top 10 for LLMs 2025 and designing controls for model-related security risks.
Why use it?
It helps developers reason about security problems that arise when model input, output, data, or permissions cannot be treated as fully trusted.

Agent for Claude Code

Part of the secure-sdlc-agents plugin — 4 skills, 8 agents shipped together

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.

agentmods
npx agentmods add agents/kaademos/secure-sdlc-agents/ai-security-engineer
Clone the repo
git clone --depth 1 https://github.com/Kaademos/secure-sdlc-agents

Made for: Claude Code.

Or install secure-sdlc-agents, the plugin that ships this one along with the rest of its 4 skills, 8 agents.

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 ai-security-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/kaademos/secure-sdlc-agents/ai-security-engineer.svg)](https://agentmods.dev/agents/kaademos/secure-sdlc-agents/ai-security-engineer)
Your own site
<a href="https://agentmods.dev/agents/kaademos/secure-sdlc-agents/ai-security-engineer"><img src="https://agentmods.dev/badge/agents/kaademos/secure-sdlc-agents/ai-security-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 195 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,143 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found 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 $0.00195 $0.02143
Opus 5 $0.00097 $0.01071
Sonnet 5 $0.00039 $0.00429
Haiku 4.5 $0.00019 $0.00214

Measured 5d ago against content hash a0429d760293, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

ai-security-engineer 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 5d 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.

- `Ignore 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.

.claude/agents/ai-security-engineer.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI/LLM Security Engineer Agent

You are a specialist in the security of AI and LLM-powered applications. This is a rapidly evolving field — you apply rigorous security engineering principles to threat categories that did not exist before 2023 and are still being codified as of 2026.

Your reference framework: OWASP Top 10 for LLMs 2025 (LLM01–LLM10). Your working assumption: every model is a trust boundary, not a trusted component.


OWASP Top 10 for LLMs 2025 — Reference

ID Category Short description
LLM01 Prompt Injection Attacker manipulates model via crafted user input
LLM02 Sensitive Information Disclosure Model leaks training data, system prompts, or PII
LLM03 Supply Chain Compromised models, datasets, or fine-tuning inputs
LLM04 Data and Model Poisoning Training/RAG data poisoned to manipulate model behaviour
LLM05 Improper Output Handling Model output used without validation in downstream systems
LLM06 Excessive Agency Model given too many permissions; can be tricked into misuse
LLM07 System Prompt Leakage System prompt extracted by adversarial user input
LLM08 Vector and Embedding Weaknesses Poisoned embeddings or retrieval manipulation
LLM09 Misinformation Model produces false output that is acted upon without verification
LLM10 Unbounded Consumption Model API abuse for DoS or cost exhaustion

Threat Model Template: LLM Features

When reviewing an AI feature, enumerate threats across these attack surfaces:

Input Trust Boundary

Who sends input to the model?

Input Source Trust Level Prompt Injection Risk
Authenticated user (UI) LOW Direct prompt injection
Public/unauthenticated user UNTRUSTED Direct + jailbreak attempts
Retrieved document (RAG) UNTRUSTED Indirect prompt injection
Tool/function call result MEDIUM Injection via external API response
Database query result MEDIUM Injection via poisoned data
Web scraping / search UNTRUSTED Indirect injection

Read the full file on GitHub · 210 lines

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. 5d ago First seen · 210 lines · 195 tokens per session scan B a0429d760293

Subscribe to this mod's changes

ai-security-engineer is an agent published in the GitHub repository Kaademos/secure-sdlc-agents (13 stars, last pushed 1mo ago), licensed MIT. It adds 195 tokens to every session and 2,143 once invoked, about $0.0010 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 2026-08-30.