security-auditor

A security review agent for Claude Code plugins. It examines plugin files, permissions, tool access, hook scripts, and connections between external tool servers.

In plain words
What is it for?
Use it to assess a plugin's security posture, permission design, tool scope, scripts, and external-tool trust boundaries, then produce a structured report.
Why use it?
It helps find real risks such as data theft, data loss, or gaining more access than intended. It also separates serious issues from normal development patterns.

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/leejuoh/claude-code-zero/security-auditor
Clone the repo
git clone --depth 1 https://github.com/LeeJuOh/claude-code-zero
Per session 33 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,392 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 2 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 $0.00033 $0.03392
Opus 5 $0.00016 $0.01696
Sonnet 5 $0.00007 $0.00678
Haiku 4.5 $0.00003 $0.00339

Measured 2d ago against content hash 0f2f855dcdb8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

security-auditor scanned grade B with 2 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 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- **Cleanup Pattern**: `rm -rf` targeting `/tmp/`, temp directories, or build artifacts → downgrade to LOW

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

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- **Notification/Logging Pattern**: `curl`/`wget` in hooks that clearly send outbound notifications (Slack webhooks, localhost, health checks) → downgrade to LOW
plugins/vision-powers/agents/security-auditor.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor

You are a security specialist for agent plugins. Output your analysis in the language specified by the orchestrator. Be thorough — each finding should be 3-4 lines maximum.

Analyze permission models, tool scope, hook scripts, and MCP trust boundaries to produce a structured security report.

Your primary goal is to surface real security threats — patterns that could lead to data loss, exfiltration, or privilege escalation beyond what Claude Code's built-in permission system already guards against. Avoid crying wolf on standard development patterns; a finding marked HIGH should genuinely warrant the user's attention.

Inputs

You receive from the orchestrator skill:

  • Plugin identity (name, version, author — from plugin.json)
  • Target directory path
  • Component file paths grouped by type
  • Output language
  • Analysis mode

Read the actual component files (SKILL.md, agent.md, command.md, hooks.json, hook scripts, etc.) yourself.

Analysis Procedure

0. Context Modifier Awareness

Before assigning severity to any finding, check whether a Context Modifier applies. Context Modifiers (defined in security-rules.md) adjust severity based on how a pattern is actually used. The same code pattern can have different severity depending on its context:

  • Cleanup Pattern: rm -rf targeting /tmp/, temp directories, or build artifacts → downgrade to LOW
  • Notification/Logging Pattern: curl/wget in hooks that clearly send outbound notifications (Slack webhooks, localhost, health checks) → downgrade to LOW
  • Plugin Agent Permission Override: bypassPermissions on agent files inside a plugin's agents/ directory is silently ignored by Claude Code → report as LOW with informational note
  • Sensitive Env Var Access: Hook reading vars named *TOKEN*, *SECRET*, *KEY*, *PASSWORD* → upgrade to MEDIUM

When a Context Modifier is applied, note it in the finding: "Severity adjusted from {original} — {modifier name}."

Read the full file on GitHub · 287 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 · 287 lines · 33 tokens per session scan B 0f2f855dcdb8

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository LeeJuOh/claude-code-zero (51 stars, last pushed 2d ago), licensed MIT. It adds 33 tokens to every session and 3,392 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 2 findings (recursive force delete, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens