audit-security

audit-security is an agent for Claude Code from RaNDoM6913/claude-code-superkit. It costs 23 tokens per session (842 once invoked), scanned A, original, MIT.

A security audit that checks an application’s source code, configuration, authentication, cross-origin rules, photo URLs, secrets, and dependencies.

In plain words
What is it for?
Use it to inspect backends, frontends, bots, and configuration for secrets in code, insecure CORS settings, authentication issues, and unsafe photo-serving URLs.
Why use it?
It helps find common security weaknesses such as exposed credentials, unsafe browser access rules, and publicly accessible private media.

Agent for Claude Code

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/random6913/claude-code-superkit/audit-security
Clone the repo
git clone --depth 1 https://github.com/RaNDoM6913/claude-code-superkit

Made for: Claude Code.

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 audit-security

README.md
[![agentmods](https://agentmods.dev/badge/agents/random6913/claude-code-superkit/audit-security.svg)](https://agentmods.dev/agents/random6913/claude-code-superkit/audit-security)
Your own site
<a href="https://agentmods.dev/agents/random6913/claude-code-superkit/audit-security"><img src="https://agentmods.dev/badge/agents/random6913/claude-code-superkit/audit-security.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 842 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 $0.00023 $0.00842
Opus 5 $0.00012 $0.00421
Sonnet 5 $0.00005 $0.00168
Haiku 4.5 $0.00002 $0.00084

Measured yesterday against content hash 5e41ccfae08e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-security 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 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.

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.

packages/showcase/.claude/agents/audit-security.md · 94 lines

How it starts

The opening of the file, as written. The whole thing — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit — SocialApp

Cross-cutting security audit across all components: backend, frontends, bots, config.

Phase 0: Load Project Context

Read if exists:

  1. CLAUDE.md or AGENTS.md — project conventions
  2. docs/architecture/ — relevant architecture docs for the task at hand

Use this context to:

  • Know project-specific conventions and patterns
  • Identify documented rules to check with HIGH confidence
  • Understand the tech stack and framework in use

Checks

1. Secrets in Code

Grep for patterns across all source:

  • API keys: [A-Za-z0-9]{32,} in string literals (filter out hashes/UUIDs)
  • Passwords: password\s*[:=]\s*["'][^"']+["'] (not in .env.example)
  • Private keys: -----BEGIN.*PRIVATE KEY-----
  • Bot tokens: [0-9]+:[A-Za-z0-9_-]{35} FAIL for any found in source code.

2. CORS Configuration

Read CORS middleware in backend/internal/app/apiapp/middleware.go. FAIL if Access-Control-Allow-Origin: * in production config. Check credentials mode consistent with origin policy.

3. Photo URL Security

Check photo-serving code in backend/internal/services/media/ and handlers. Verify URLs are presigned (TTL-limited), not permanent public URLs. WARN if raw S3/MinIO paths could reach client responses.

4. Phone Number Isolation

Verify phone is stored in user_private table only (not profiles or users). Grep phone columns in migration files. FAIL if phone storage outside user_private. Check no API response leaks phone to other users.

5. initData Validation

Read backend/internal/services/auth/service.go. Check: HMAC-SHA256 validation, auth_date freshness, constant-time comparison. WARN for missing components.

6. Missing .env Files

Check existence: backend/.env, tgbots/bot_moderator/.env, tgbots/bot_support/.env. WARN if missing (needed for local dev).

7. Stale localStorage Keys

Grep localStorage\.(getItem|setItem) in frontend/src/. List all keys. WARN for keys referencing removed features.

Read the full file on GitHub · 94 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 · 94 lines · 23 tokens per session scan A 5e41ccfae08e

Subscribe to this mod's changes

audit-security is an agent published in the GitHub repository RaNDoM6913/claude-code-superkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 842 once invoked, about $0.0001 per session on Opus 5. 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 2026-09-03.

Related

Other agents, from other repositories

python-architect

Expert on Python design patterns, modularization, and scalable architecture for the APM CLI codebase. Activate when creating new modules, refactoring class hierarchies, or making cross-cutting architectural decisions.

microsoft/apm · 45 tokens

doc-writer

APM documentation writer. Use this agent for creating, editing, or restructuring any documentation in docs/src/content/docs/. Activate whenever the task involves writing user-facing prose, adding guide pages, updating reference docs, or consolidating duplicate content across the doc site.

microsoft/apm · 51 tokens

cdo

APM Chief Documentation Officer. Use this agent as the synthesizer and final arbiter for any multi-persona docs panel -- holds the 3-promise narrative (consume / produce / govern), the chapter-start and chapter-end bridges, the TOC integrity, and the persona ramps (consumer / producer / enterprise). Activate to…

microsoft/apm · 95 tokens

algorithmic-patterns

Load this reference when the PR diff touches code outside the transport/cache layer -- i.e. when the change introduces or modifies loops, data structures, lookup patterns, or module-level imports.

microsoft/apm · 0 tokens

apm-expert

Expert on APM (Agent Package Manager). Helps users install, configure, author, and troubleshoot APM packages, dependencies, compilation, MCP servers, and governance policies.

microsoft/apm · 39 tokens

test-coverage-expert

Test-coverage expert paired with the DevX UX lens. Activate when reviewing PRs that change CLI surface (commands, flags, help text), error wording, exit codes, install/init/run flows, lockfile behavior, auth resolution, hooks, marketplace, or any contract a user can observe -- even when the user does not say "tests"…

microsoft/apm · 151 tokens