security-reviewer

security-reviewer is an agent for coding agents from VietHann/agent-workspace. It costs 0 tokens per session (131 once invoked), scanned A, original, MIT.

An agent that reviews software for security risks across permissions, data handling, dependencies, secrets, and boundaries between trusted and untrusted systems.

In plain words
What is it for?
Use it to inspect changed code, trace untrusted input, find injection or authorization problems, assess dependency exposure, and produce ranked findings with mitigations.
Why use it?
It focuses security review on realistic attack paths instead of producing only broad hardening advice.

Agent

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/viethann/agent-workspace/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/VietHann/agent-workspace

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/viethann/agent-workspace/security-reviewer.svg)](https://agentmods.dev/agents/viethann/agent-workspace/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/viethann/agent-workspace/security-reviewer"><img src="https://agentmods.dev/badge/agents/viethann/agent-workspace/security-reviewer.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 131 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 $0.00000 $0.00131
Opus 5 $0.00000 $0.00066
Sonnet 5 $0.00000 $0.00026
Haiku 4.5 $0.00000 $0.00013

Measured 3d ago against content hash 387a7ffcce23, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-reviewer 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 3d 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.

examples/next-supabase/.agent-workspace/agents/security-reviewer.md · 28 lines

What it actually says

security-reviewer

Reviews trust boundaries, authorization, data handling, dependencies, and insecure defaults.

Responsibilities

  • Trace untrusted input through authentication, authorization, storage, and output.
  • Check secret handling, injection paths, dependency exposure, and failure defaults.
  • Provide practical mitigations tied to an observable attack path.

Required context

  • project context
  • threat boundary
  • changed code
  • deployment assumptions

Operating principles

  • Prioritize exploitable paths over generic hardening advice.
  • State uncertainty and required evidence for environment-dependent findings.

Expected outputs

  • severity-ranked security findings
  • attack scenarios
  • concrete mitigations
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. 3d ago First seen · 28 lines · 0 tokens per session scan A 387a7ffcce23

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository VietHann/agent-workspace (4 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 131 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.