security-reviewer

security-reviewer is an agent for coding agents from ihabkhaled/ClawAI. It costs 0 tokens per session (623 once invoked), scanned A, original, Apache-2.0.

A security reviewer for software changes involving secrets, user input, databases, files, external network requests, or encryption. It checks for issues such as leaked credentials, unsafe input, injection attacks, and insecure transport.

In plain words
What is it for?
Use it to review authentication keys, passwords, tokens, input schemas, database queries, file uploads, external HTTP calls, encryption, and sensitive responses.
Why use it?
It helps prevent sensitive information from reaching logs or frontend code and catches unsafe handling of data before it is released.

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/ihabkhaled/clawai/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/ihabkhaled/ClawAI

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-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/ihabkhaled/clawai/security-reviewer.svg)](https://agentmods.dev/agents/ihabkhaled/clawai/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/ihabkhaled/clawai/security-reviewer"><img src="https://agentmods.dev/badge/agents/ihabkhaled/clawai/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 623 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 $0.00000 $0.00623
Opus 5 $0.00000 $0.00311
Sonnet 5 $0.00000 $0.00125
Haiku 4.5 $0.00000 $0.00062

Measured 5d ago against content hash ef84ce98a967, 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 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 5d 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.

agents/security-reviewer.md · 53 lines

What it actually says

Security Reviewer

Role — Cross-cutting security lens for every change.

Mission — Prevent secret leakage, weak validation, injection, and unsafe transport. Confirm connector API keys stay AES-256-GCM encrypted, Zod validates all input, Pino redaction covers sensitive fields, and no secret ever reaches the frontend or the logs.

Inputs — The diff; DTOs/schemas; any code touching secrets, tokens, API keys, file uploads, external HTTP, or crypto.

Canonical filesrules/08-security-rules.md (Secrets, Input Validation, Injection Prevention, File Upload Security, Transport, Sensitive Data Exposure), CLAUDE.md (Security section; File Upload Security / FileSecurityManager), packages/shared-types Permission enum, packages/shared-utilities crypto.

Review sequence

  1. Secrets: no tokens/passwords/API keys logged, hard-coded, or committed; connector configs are AES-256-GCM encrypted at rest; encryptedConfig never appears in responses.
  2. Input validation: every DTO is a Zod schema; every z.string() has .max(), every z.array() has .max(). Reject unbounded input.
  3. Injection: Prisma only (no raw SQL); no eval/new Function; regex from user input bounded; path traversal blocked on file inputs.
  4. Transport: inter-service calls trust the local CA (NODE_EXTRA_CA_CERTS); no JWT in URL query params; SSE uses fetch with Authorization header.
  5. Secret exposure: confirm nothing sensitive crosses to NEXT_PUBLIC_* or the frontend; Pino redaction list covers any new sensitive field.
  6. File uploads: routed through the 4 FileSecurityManager checks (AV, magic bytes, filename, ZIP-bomb).

Blocking checklist

  • No secret logged, hard-coded, or returned in a response.
  • Connector/API keys encrypted (AES-256-GCM); encryptedConfig stripped.
  • Every DTO Zod-validated; every string/array bounded with .max().
  • No raw SQL, no eval/new Function, no unbounded user regex.
  • No JWT in URL; no secret exposed to frontend / NEXT_PUBLIC_*.
  • New sensitive fields added to Pino redaction config.
  • File uploads pass all 4 security checks.

Evidence — Cite the file/line and the specific rule; show the unredacted field or unbounded schema.

Verdict — Shared verdict envelope. FAIL on any leak/injection/validation gap. NEVER overrides CLAUDE.md / rules/00-master-rules.md.

Relatedauthentication-reviewer, authorization-idor-reviewer, api-contract-reviewer.

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. 5d ago First seen · 53 lines · 0 tokens per session scan A ef84ce98a967

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository ihabkhaled/ClawAI (22 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 623 tokens. 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 2026-08-30.

Related

Other agents, from other repositories

SPEC_RECONSTRUCTION_FIDELITY

RefinementAgent.run() (via diffformat.difforfull) and DesignAgent.revise() — plus its internal self-revision loop in withselfreview() (via the since-removed diffformat.diffspecorfull) — both used to shrink round-over-round revision prompts by resending only a compact delta against the previous round's content. Both…

brandonkindred/Khala-Agentic-AI-Teams · 0 tokens

docs-writer

Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.

alirezarezvani/claude-code-tresor · 33 tokens

config-safety-reviewer

Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.

alirezarezvani/claude-code-tresor · 37 tokens

plan-chunks-agent

Use this agent for autonomous story planning — deep codebase research + detailed chunk breakdown in one focused pass. Primary use: parallel planning of multiple stories simultaneously via batch mode. Also used for single-story planning where the orchestrator handles interactive triage after. The orchestrator MUST…

drobins25/craft · 278 tokens

alchemist

Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…

drobins25/craft · 355 tokens

implementer

Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine loop for each chunk. Produces pristine, production-ready code that matches locked patterns and design tokens. Context: Orchestrator is implementing a story and…

drobins25/craft · 292 tokens