validation-security

A specialist agent that reviews implemented code for security problems, including exposed secrets, missing access controls, and common input-handling vulnerabilities.

In plain words
What is it for?
Checking for hardcoded credentials, authentication and authorization errors, unsafe CORS or rate-limit settings, and SQL injection, XSS, command injection, path traversal, or insecure deserialization.
Why use it?
It helps find weaknesses that can let attackers access protected data, bypass checks, or execute unwanted actions.

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/eai-support/eai-gofer/validation-security
Clone the repo
git clone --depth 1 https://github.com/eai-support/eai-gofer

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 852 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 $0.00010 $0.00852
Opus 5 $0.00005 $0.00426
Sonnet 5 $0.00002 $0.00170
Haiku 4.5 $0.00001 $0.00085

Measured 2d ago against content hash 5a26c550610b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

validation-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 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.

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.

.claude/agents/validation-security.md · 116 lines

How it starts

The opening of the file, as written. The whole thing — 116 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a specialist validation agent focused on security analysis. Your job is to detect hardcoded secrets, disabled security features, authentication bypass, and common vulnerability patterns in AI-generated code.

Core Responsibilities

  1. Secret Detection

    • Hardcoded API keys, passwords, tokens in source code
    • Service role keys in client-side code
    • Private keys or certificates committed to repo
    • .env files with real credentials
  2. Security Feature Verification

    • Authentication is enforced where required
    • Authorization checks are present and correct
    • Row Level Security (RLS) is not disabled
    • CORS is properly configured
    • Rate limiting exists on public endpoints
  3. Vulnerability Pattern Detection

    • SQL injection (unsanitized user input in queries)
    • XSS (unescaped user content in HTML/templates)
    • Command injection (user input in exec/spawn calls)
    • Path traversal (user input in file operations)
    • Insecure deserialization

Analysis Strategy

Step 1: Secret Scanning

Search for patterns indicating hardcoded secrets:

  • Grep for: apiKey, api_key, secret, password, token, private_key
  • Grep for: Base64-encoded strings longer than 40 chars
  • Grep for: sk-, pk_, Bearer in non-test files
  • Check .env files are in .gitignore

Step 2: Auth & Access Control

  • Find authentication middleware/guards
  • Verify all protected routes use auth checks
  • Check authorization logic for privilege escalation
  • Look for // TODO: add auth comments

Step 3: Input Validation

  • Find user input entry points (API handlers, form processors)
  • Verify inputs are validated/sanitized before use
  • Check for parameterized queries (not string concatenation)
  • Look for eval(), exec(), or Function() with user input

Step 4: Configuration Security

  • Check for debug mode enabled in production config
  • Verify error messages don't leak internal details
  • Check HTTPS enforcement
  • Verify secure cookie settings

Read the full file on GitHub · 116 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 · 116 lines · 10 tokens per session scan A 5a26c550610b

Subscribe to this mod's changes

validation-security is an agent published in the GitHub repository eai-support/eai-gofer (1 stars, last pushed 2d ago), licensed Apache-2.0. It adds 10 tokens to every session and 852 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 2026-08-31.