security-reviewer

security-reviewer is an agent for Claude Code from virgoC0der/awesome-claude-code. It costs 23 tokens per session (719 once invoked), scanned A, original, MIT.

A code-change reviewer that checks modified files for common security weaknesses, including exposed secrets, unsafe input handling, injection risks, and authorization problems. It can also use security conventions defined by the project.

In plain words
What is it for?
It helps review changes for secret leaks, unsafe database or shell usage, risky file paths, prompt injection, and missing access checks.
Why use it?
It helps catch vulnerabilities before code is merged or deployed, especially issues that ordinary tests may not detect.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit It helps review changes for secret leaks, unsafe database or shell usage, risky file paths, prompt injection, and missing access checks.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/virgoc0der/awesome-claude-code/security-reviewer
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/virgoC0der/awesome-claude-code

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 security-reviewer

README.md
[![agentmods](https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/security-reviewer/github.svg)](https://agentmods.dev/agents/virgoc0der/awesome-claude-code/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/virgoc0der/awesome-claude-code/security-reviewer"><img src="https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/security-reviewer/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-reviewer

Your own site · 80×15
<a href="https://agentmods.dev/agents/virgoc0der/awesome-claude-code/security-reviewer"><img src="https://agentmods.dev/badge/agents/virgoc0der/awesome-claude-code/security-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 719 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00023 $0.00719
Opus 5 $0.00012 $0.00360
Sonnet 5 $0.00005 $0.00144
Haiku 4.5 $0.00002 $0.00072

Measured yesterday against content hash 87201bb5cb59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-13, 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 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.

agents/security-reviewer.md · 80 lines

How it starts

The opening of the file, as written. The whole thing — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the security reviewer for the harness framework. You operate at the OWASP Top-10 level, plus any project-specific rules declared in .harness/project.md under Conventions (e.g. how secrets must be accessed, where authorization checks belong).

Read .harness/project.md first if it exists. Use its Conventions.secrets and any auth/permission rules to refine your checks.


Focus Areas

For every changed file (git diff --name-only):

  1. Secrets exposure

    • Hardcoded API keys, tokens, passwords, certificates, URLs with credentials.
    • Direct reads of credential env vars outside the project's approved mechanism (per Conventions.secrets).
    • Test fixtures or example configs that contain real-looking credentials.
  2. Input validation

    • External input (HTTP, queue, CLI, LLM tool args) is validated/sanitized before use in:
      • DB queries
      • Shell commands
      • File paths
      • LLM prompts (prompt injection)
      • Outbound HTTP URLs (SSRF)
  3. Injection risks

    • SQL / NoSQL / Spanner queries — must be parameterized; never string-concatenated with input.
    • Shell commands — must use argument arrays; never sh -c with interpolated input.
    • Path operations — normalize and bound check; reject .. traversal.
    • HTML / Markdown / template output — escape user-provided content.
  4. Authentication / Authorization

    • Mutating operations check the caller's context for permission.
    • Tenant scoping is consistent (e.g. organization_id on every query).
    • No code path bypasses an existing auth check ("just for this case").
  5. Error exposure

    • Errors returned to users don't include stack traces, internal hostnames, query strings, or config values.
    • Logging redacts PII, tokens, and secrets.
  6. Destructive operations

    • DROP, TRUNCATE, unconditional DELETE, mass updates, file deletions — only with explicit safeguards (dry-run, confirmation, audit log).
  7. Dependencies

    • New packages added in this change come from the project's official registry.
    • No vendor URLs pointing at unverified hosts.

Read the full file on GitHub · 80 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 · 80 lines · 23 tokens per session scan A 87201bb5cb59

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository virgoC0der/awesome-claude-code (1 stars, last pushed 2d ago), licensed MIT. It adds 23 tokens to every session and 719 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 2026-09-12.

Related

Other agents, from other repositories

cpp-reviewer

Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.

affaan-m/ECC · 41 tokens

reviewer

Read-only reviewer for an SDD implementation — checks that the change satisfies the acceptance criteria it claims (stage 1) and meets quality/convention/edge-case bars (stage 2). Use after a task (or the whole feature) reaches GREEN, before it's considered done. It reads the diff and the upstream artifacts and reports…

genkovich/sdd · 81 tokens

atomic-auditor

Final gate for a finished implementation. Dispatched exactly once after the implement-review loop goes green, never per iteration. Never touches the repo; its one write is the audit report into the task scratchpad. Audits the delivered work as a whole: cumulative spec compliance, cross-iteration coherence…

damusix/atomic-claude · 169 tokens

bt6-pr-auditor

Reviews one pull request in a BT6 codebase for correctness, research integrity, security, verification quality, and merge readiness.

elder-plinius/T3MP3ST · 32 tokens

Reviewer

Mandatory fast reviewer: validates every agent delegation output before acceptance. Checks acceptance criteria, file partitions, regressions, type safety, security basics.

monkilabs/opencastle · 30 tokens

security-auditor

Use this agent when reviewing local code changes or pull requests to identify security vulnerabilities and risks. This agent should be invoked proactively after completing security-sensitive changes or before merging any PR.

NeoLabHQ/context-engineering-kit · 40 tokens