agentmods.dev

security-auditor

security-auditor is an agent for Claude Code from datit309/supergraph. It costs 56 tokens per session (1,023 once invoked), scanned B, original, MIT.

A coding assistant that reviews application changes for security weaknesses. It checks code differences, web endpoints, and data flows for issues such as unauthorised access, injection, cross-site scripting, request forgery, and exposed secrets.

In plain words
What is it for?
Use it to audit a set of Git changes, API endpoints, authentication and authorisation code, database queries, file or shell operations, and network calls against common web security risks.
Why use it?
It helps find security problems before code is merged, including cases where users can access another user's data or attackers can influence database or network requests.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions subagents.

Part of the supergraph plugin — 42 skills, 7 agents, 6 hooks shipped together

not rated 22repo yesterday B scan 56 tokens original MIT

Good fit Use it to audit a set of Git changes, API endpoints, authentication and authorisation code, database queries, file or shell operations, and network calls against common web security risks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/datit309/supergraph/security-auditor
View source ↗ datit309/supergraph datit309.github.io
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.

Clone the repo
git clone --depth 1 https://github.com/datit309/supergraph

Made for: Claude Code.

Or install supergraph, the plugin that ships this one along with the rest of its 42 skills, 7 agents, 6 hooks.

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-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/datit309/supergraph/security-auditor/github.svg)](https://agentmods.dev/agents/datit309/supergraph/security-auditor)
Your own site
<a href="https://agentmods.dev/agents/datit309/supergraph/security-auditor"><img src="https://agentmods.dev/badge/agents/datit309/supergraph/security-auditor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-auditor

Your own site · 80×15
<a href="https://agentmods.dev/agents/datit309/supergraph/security-auditor"><img src="https://agentmods.dev/badge/agents/datit309/supergraph/security-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 56 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,023 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00056 $0.01023
Opus 5.5 $0.00022 $0.00409
Sonnet 5.5 $0.00011 $0.00205
Haiku 4.5 $0.00006 $0.00102

Measured yesterday against content hash 05b2e92bb0cf, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade B, and why

security-auditor scanned grade B 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 yesterday.

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.

Cloud metadata endpointmediumServer-side request forgery

One request to 169.254.169.254 can return temporary IAM credentials.

- Is there an IP allowlist blocking private IP ranges (`127.0.0.1`, `169.254.169.254`, `10.0.0.0/8`, `192.168.0.0/16`)?

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

plugins/supergraph/agents/security-auditor.md · 103 lines

How it starts

The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Auditor Agent

Act as an independent Senior Application Security Engineer. Audit code changes, architectural boundaries, and endpoints for security vulnerabilities before merge. Do not write feature code; focus exclusively on finding security flaws, data leaks, and authorization bypasses.

Inputs Expected

The prompt must provide:

  • Scope of changes: BASE_SHA and HEAD_SHA, or list of modified files
  • Description of feature or architectural context
  • Optional API / endpoint specifications

Process

Implementers of this role must not spawn subagents. Inspect changes directly and return a bounded Security Audit Report to the controller.

1. Inspect Changed Files and Diffs

git diff --stat BASE_SHA..HEAD_SHA
git diff BASE_SHA..HEAD_SHA

Identify all external-facing attack surfaces:

  • HTTP / REST / GraphQL endpoints
  • Database query construction
  • Authentication / Authorization middleware and guards
  • File system, shell, or network socket interactions

2. Deep Vulnerability Audit (OWASP Top 10 & Vibesec)

Examine changes against critical vulnerability categories:

  1. Broken Object Level Authorization (BOLA / IDOR):

    • Does every query fetching resource by id explicitly check ownership (WHERE id = :id AND user_id = :currentUser)?
    • Can User A manipulate parameters to read/modify User B's resources?

  2. Injection (SQLi, NoSQL, Command, Path Traversal):

    • Are SQL queries strictly parameterized? Look for string concatenation (f"SELECT ... {var}", query + req.body).
    • Are shell execution calls (exec, spawn, subprocess) avoided or sanitized?
    • Are file paths validated against path traversal (../)?

  3. Cross-Site Scripting (XSS) & Template Injection:

    • Are user inputs escaped before rendering?
    • Check for dangerouslySetInnerHTML, v-html, innerHTML, unescaped markdown.

  4. Authentication, JWT & Session Management:

    • Is JWT signature and expiration verified? Is algorithm pinned (preventing alg: none or HMAC/RSA confusion)?
    • Are passwords hashed using bcrypt/argon2 with sufficient cost?
    • Are sensitive session cookies marked HttpOnly; Secure; SameSite=Strict/Lax?

Read the full file on GitHub · 103 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. yesterday First seen · 103 lines · 56 tokens per session scan B 05b2e92bb0cf

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository datit309/supergraph (22 stars, last pushed yesterday), licensed MIT. It adds 56 tokens to every session and 1,023 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (cloud metadata endpoint). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-16.

Git and workflowSecurityantigravity-pluginantigravity-skillsclaude-pluginclaude-skillscodex-plugincodex-skills
Related

Other agents, from other repositories

diff-reviewer

Reviews an existing working-tree diff for correctness, scope creep, suppressed errors and shortcut fixes. Reports findings only — never edits. Use as a second opinion before the driver accepts a worker's changes.

aiskillstore/marketplace · 43 tokens

pipeline-auto-brain

Use only when superb:pipeline-auto dispatches its three brains — to answer one blocking question in a quorum, or at stage 02 to propose the open decisions for the one human gate. One of three independently-briefed readers; returns one strict JSON object in the shape its prompt names, nothing else. Never dispatched by…

kardebadas/claude-plugin · 73 tokens

bug-investigator

Use when a bug, regression, or unexpected behaviour needs its root cause traced to specific code before any fix is designed. Investigates only — never edits files. Returns a structured report citing file:line evidence.

kardebadas/claude-plugin · 46 tokens

pipeline-auto-intent-reader

Use only at superb:pipeline-auto stage 01, to read what the user actually asked for and return it as a strict JSON hypothesis. One of three independent readers. Reads and reports; never designs, never proposes, never chooses a stack.

kardebadas/claude-plugin · 55 tokens

claim-validator

Use this agent to validate specific factual claims extracted from AI context files against the actual codebase — checks paths, versions, symbols, counts, commands, and dependencies.

knitli/toolshed · 36 tokens

architecture-discovery

Use when a product idea needs its technical decisions surfaced as questions before any of them are made — invoked by superb:craft once per session, after the idea is stated and before the first question round, for software projects whose stack is not yet decided. Returns candidate questions only; never chooses a stack…

kardebadas/claude-plugin · 68 tokens