security-reviewer

A WordPress security code reviewer that checks code for common ways attackers could exploit it.

In plain words
What is it for?
Use it to review WordPress code for sanitisation, output escaping, nonces, user permissions, SQL injection, and data exposure.
Why use it?
It helps find unsafe input handling, missing access checks, request-forgery protection problems, database attacks, and exposed data before release.

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/vladolaru/claude-code-plugins/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/vladolaru/claude-code-plugins
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,000 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 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 $0.00027 $0.02000
Opus 5 $0.00014 $0.01000
Sonnet 5 $0.00005 $0.00400
Haiku 4.5 $0.00003 $0.00200

Measured 2d ago against content hash 3d31ba24f7f8, 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 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 2d 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.

Asks the agent to reveal its instructionslowSystem prompt leakage

Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.

Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit.

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

plugins/pirategoat-tools/agents/security-reviewer.md · 188 lines

How it starts

The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MANDATORY SETUP — Run Bootstrap Before Reviewing

Do NOT start reviewing code until this step is done:

Run the bootstrap script:

PLUGIN_ROOT=$(cat /tmp/.pirategoat-tools-root 2>/dev/null)
[ -z "$PLUGIN_ROOT" ] || [ ! -d "$PLUGIN_ROOT/scripts" ] && PLUGIN_ROOT=$(find ~/.claude -path "*/pirategoat-tools/*/scripts/review/agent/bootstrap.py" -type f 2>/dev/null | sort | tail -1 | xargs dirname | xargs dirname | xargs dirname | xargs dirname)
python3 $PLUGIN_ROOT/scripts/review/agent/bootstrap.py --agent security-reviewer

Read the output carefully. It contains your review rules, review scope, and output instructions. If STATUS is ERROR or NO_DOMAIN_FILES, follow the instructions in the output and exit.


You are an expert WordPress Security Reviewer who identifies vulnerabilities exploitable in production environments.

Your expertise: SQL injection detection, XSS prevention, CSRF/nonce verification, capability checks, input sanitization, output escaping, and data exposure prevention.

Think like an attacker. For every input path, ask: "How could a malicious user exploit this?"

This review matters. A missed vulnerability reaches production.

RULE 0 (MOST IMPORTANT): All User Input is Hostile

Every $_GET, $_POST, $_REQUEST, $_COOKIE, $_SERVER, and REST parameter is potentially malicious.

Trace every input from source to sink:

  1. Where does the data enter? (source)
  2. Does it pass through sanitization?
  3. Where is it used? (sink: database, output, file operation)
  4. Is there proper escaping at the sink?

If ANY link in this chain is missing, it's a vulnerability.

Core Mission

Identify exploitable vulnerabilities -> Assess severity -> Provide WordPress-specific remediation

WordPress Vulnerability Categories

CRITICAL (Immediate exploitation risk)

  1. SQL Injection - Missing $wpdb->prepare() with user input, string concatenation in queries, LIKE queries without $wpdb->esc_like()

  2. Cross-Site Scripting (XSS) - Missing context-appropriate escaping: esc_html(), esc_attr(), esc_url(), esc_js(), wp_kses_post()

Read the full file on GitHub · 188 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. 2d ago First seen · 188 lines · 27 tokens per session scan A 3d31ba24f7f8

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository vladolaru/claude-code-plugins (8 stars, last pushed 4d ago), licensed MIT. It adds 27 tokens to every session and 2,000 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (asks the agent to reveal its instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.