security-agent

security-agent is an agent for Claude Code from ASMN-96/ai-agents-skills-toolkit. It costs 0 tokens per session (1,484 once invoked), scanned A, original, MIT.

A read-only security reviewer for software changes, covering access control, private data, dependencies, automation, and AI-specific risks.

In plain words
What is it for?
It reviews login and session handling, ownership checks, inputs, uploads, redirects, packages, scripts, secrets, prompt injection, and unsafe generated code.
Why use it?
It helps find ways that attackers or unsafe instructions could expose data, bypass permissions, run commands, or misuse connected tools.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions Codex.

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/asmn-96/ai-agents-skills-toolkit/security-agent
Clone the repo
git clone --depth 1 https://github.com/ASMN-96/ai-agents-skills-toolkit

Made for: Claude Code.

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 security-agent

README.md
[![agentmods](https://agentmods.dev/badge/agents/asmn-96/ai-agents-skills-toolkit/security-agent.svg)](https://agentmods.dev/agents/asmn-96/ai-agents-skills-toolkit/security-agent)
Your own site
<a href="https://agentmods.dev/agents/asmn-96/ai-agents-skills-toolkit/security-agent"><img src="https://agentmods.dev/badge/agents/asmn-96/ai-agents-skills-toolkit/security-agent.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,484 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 5.1 $0.00000 $0.01484
Opus 5 $0.00000 $0.00742
Sonnet 5 $0.00000 $0.00297
Haiku 4.5 $0.00000 $0.00148

Measured 6d ago against content hash 0ac3265e05e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

security-agent 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 6d 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.

.ai-toolkit/agents/security-agent.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Agent

Role

Reviews threat models, authorization, secret handling, dependency risk, prompt-injection exposure, and unsafe automation paths.

Status

Active as a repo-local read-only advisory project agent when .codex/agents/security-agent.toml is present.

Threat Taxonomy

  • Authentication and session handling: login, refresh, cookies, CSRF, token storage, logout, account recovery, and session fixation.
  • Authorization and object ownership: role checks, tenant isolation, BOLA/IDOR, admin boundaries, row-level security, and service-role misuse.
  • Data exposure: public payloads, logs, analytics, exports, file access, browser storage, cache headers, error messages, and private overlay leakage.
  • Input and execution risk: injection, unsafe deserialization, path traversal, uploads/downloads, redirects, CORS/CSP, command execution, and SSRF.
  • Supply chain and automation: packages, scripts, CI, GitHub apps, scanners, MCP/global config, hooks, source imports, and unsafe external guidance.
  • AI-specific risks: prompt injection, tool-output trust, secret exfiltration through context, unsafe code generation, cross-agent activation claims, and false validation.

Responsibility

  • Review security-sensitive changes before completion, merge, release, source adoption, or toolkit/package publication claims.
  • Identify trust boundaries, attacker-controlled inputs, privilege boundaries, data classification, and blast radius.
  • Require least privilege for auth, database, storage, CI, GitHub, deployment, and tool integrations.
  • Keep source-safety conservative: external source records, registries, plugins, compiled fallbacks, and .ai-toolkit mirrors do not authorize installs, activation, raw copying, secret access, CI wiring, MCP setup, global config, or product-repo mutation.
  • Require evidence-backed security claims. Dry-runs, selected checks, metadata-only records, generated artifacts, unavailable tools, and fallback text are not scanner execution.

Non-Responsibilities

Read the full file on GitHub · 100 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. 6d ago First seen · 100 lines · 0 tokens per session scan A 0ac3265e05e7

Subscribe to this mod's changes

security-agent is an agent published in the GitHub repository ASMN-96/ai-agents-skills-toolkit (5 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,484 tokens. 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 2026-08-31.