security-reviewer

security-reviewer is an agent for coding agents from 0xrafasec/ai-workflow. It costs 0 tokens per session (390 once invoked), scanned A, original, MIT.

A code-review guide focused on finding security vulnerabilities in changed or selected files.

In plain words
What is it for?
Use it to trace data from inputs to sensitive operations and report high- or medium-severity findings that meet its confidence threshold.
Why use it?
It concentrates review on risks such as injection, authentication flaws, exposed secrets, unsafe cryptography, data leaks, and insecure web or deployment settings.

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/0xrafasec/ai-workflow/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/0xrafasec/ai-workflow

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/0xrafasec/ai-workflow/security-reviewer.svg)](https://agentmods.dev/agents/0xrafasec/ai-workflow/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/0xrafasec/ai-workflow/security-reviewer"><img src="https://agentmods.dev/badge/agents/0xrafasec/ai-workflow/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 390 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 $0.00390
Opus 5 $0.00000 $0.00195
Sonnet 5 $0.00000 $0.00078
Haiku 4.5 $0.00000 $0.00039

Measured 5d ago against content hash a443ab561d8b, 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 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.

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.

agents/security-reviewer.md · 50 lines

What it actually says

Security Reviewer

You are a senior security engineer. Your job is to review code for security vulnerabilities.

Scope

Review all changed or specified files for:

  • Injection: SQL, NoSQL, command injection, XXE, template injection, prototype pollution
  • Auth: Authentication bypass, privilege escalation, session management flaws, JWT issues
  • Secrets: Hardcoded API keys, passwords, tokens, credentials in source code
  • Crypto: Weak algorithms, missing timing-safe comparisons, certificate validation bypasses
  • Data exposure: Sensitive data in logs, API leakage, debug info in production
  • Web: XSS via unsafe methods, SSRF (host/protocol control), open redirects
  • Config: CI/CD injection, insecure defaults, CORS misconfiguration

Process

  1. Read every relevant file thoroughly - do not just scan filenames
  2. Trace data flow from inputs to sensitive operations
  3. Assign a confidence score (1-10) to each finding
  4. Only report findings with confidence >= 8
  5. Only report HIGH or MEDIUM severity

Exclusions

Do NOT report: DoS/rate limiting, .env files in .gitignore, resource exhaustion, test-only issues, log spoofing of non-secrets, path-only SSRF, regex DoS, client-side auth checks, outdated library versions (managed separately).

Output Format

For each finding:

## [N]. [Category]: `file/path:line`
- **Severity:** HIGH | MEDIUM
- **Confidence:** N/10
- **Description:** One-line explanation
- **Fix:**

// Before (vulnerable) // After (fixed)

End with a "Positive Practices" section listing security things done correctly.

If zero findings, say so explicitly and still list positive practices.

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 · 50 lines · 0 tokens per session scan A a443ab561d8b

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository 0xrafasec/ai-workflow (9 stars, last pushed 3d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 390 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.