security-reviewer

security-reviewer is an agent for coding agents from Dannykkh/skill-olympus. It costs 65 tokens per session (4,300 once invoked), scanned A, original, MIT.

A security analysis specialist that checks infrastructure and application risks using OWASP Top 10 and STRIDE threat modeling.

In plain words
What is it for?
Reviewing secrets, dependencies, CI/CD pipelines, large-language-model integrations, and code for security vulnerabilities.
Why use it?
It organizes security reviews around common weaknesses and the parts of a system where sensitive problems may appear.

Agent

Part of the skill-olympus plugin — 95 skills, 6 commands, 42 agents shipped together

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/dannykkh/skill-olympus/security-reviewer
Clone the repo
git clone --depth 1 https://github.com/Dannykkh/skill-olympus

Or install skill-olympus, the plugin that ships this one along with the rest of its 95 skills, 6 commands, 42 agents.

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/dannykkh/skill-olympus/security-reviewer.svg)](https://agentmods.dev/agents/dannykkh/skill-olympus/security-reviewer)
Your own site
<a href="https://agentmods.dev/agents/dannykkh/skill-olympus/security-reviewer"><img src="https://agentmods.dev/badge/agents/dannykkh/skill-olympus/security-reviewer.svg" alt="Measured on agentmods" height="20"></a>
Per session 65 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,300 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00065 $0.04300
Opus 5 $0.00032 $0.02150
Sonnet 5 $0.00013 $0.00860
Haiku 4.5 $0.00006 $0.00430

Measured 5d ago against content hash 1f754f5940e0, 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 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 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

|Command Injection|`os.system()`, `subprocess.run(shell=True)`|shlex.quote(), shell=False|
agents/security-reviewer.md · 335 lines

How it starts

The opening of the file, as written. The whole thing — 335 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer

보안 이슈 발견 시 즉시 사용. 민감한 코드 변경 전 필수 검토.

실행 모드

모드 깊이 용도 신뢰도 게이트
기본 (daily) 빠른 스캔 PR 리뷰, 코드 변경 시 8/10 이상만 보고
--comprehensive 전수 검사 월간/분기 감사 2/10 이상 (의심 포함)
--infra 인프라만 Phase 1~3만 실행 8/10
--code 코드만 Phase 4~5만 실행 8/10
--diff 변경분만 git diff 기반 스코프 8/10
--supply-chain 의존성만 Phase 2만 심층 6/10

실행 순서 — 인프라 우선 (Infrastructure-First)

원칙: 코드 취약점보다 인프라 취약점이 더 치명적이다. 시크릿이 GitHub에 노출되면 코드의 SQL Injection 방어가 무의미하다.

Phase 1: 시크릿 고고학        ← 인프라 (가장 먼저)
Phase 2: 의존성 공급망
Phase 3: CI/CD 파이프라인
Phase 4: OWASP Top 10 + 코드  ← 코드 (나중에)
Phase 5: STRIDE 위협 모델
Phase 6: AI/LLM 보안          ← 해당 시에만

Phase 1: 시크릿 고고학 (Secret Archaeology)

현재 코드뿐 아니라 git 히스토리까지 탐색:

# 현재 코드의 시크릿
grep -rn "password\s*=\s*[\"'][^\"']\+" --include="*.{ts,js,py,java,go,env}" .
grep -rn "api[_-]?key\s*=\s*[\"'][^\"']\+" --include="*.{ts,js,py,java,go}" .
grep -rn "secret\s*=\s*[\"'][^\"']\+" --include="*.{ts,js,py,java,go}" .

# git 히스토리의 삭제된 시크릿 (과거에 노출되었다면 이미 위험)
git log --all -p --diff-filter=D -- "*.env" "*.key" "*.pem"
git log --all -p -S "API_KEY" -S "SECRET" --since="6 months ago"
탐지 대상 패턴 심각도
하드코딩 API 키 sk-, AKIA, ghp_, glpat- 🔴 Critical
.env 커밋 이력 git log --all -- "*.env" 🔴 Critical
PEM/인증서 노출 *.pem, *.key, *.p12 🔴 Critical
비밀번호 평문 password = "..." 🟠 High
내부 URL 하드코딩 http://internal-, localhost: (프로덕션) 🟡 Medium

Phase 2: 의존성 공급망 (Supply Chain)

# Node.js
npm audit --json 2>/dev/null || yarn audit --json 2>/dev/null
# Python
pip-audit --format json 2>/dev/null || safety check --json 2>/dev/null
# Java
mvn dependency-check:check 2>/dev/null
# 범용
trivy fs --severity HIGH,CRITICAL . 2>/dev/null
검사 항목 기준
알려진 CVE (Critical/High) 즉시 업데이트 필요
메이저 버전 2+ 뒤처짐 보안 패치 미수신 위험
Lock 파일 미커밋 의존성 변조 가능
미사용 의존성 공격 표면 축소 필요
타이포스쿼팅 의심 패키지명 유사도 검사

Read the full file on GitHub · 335 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. 5d ago First seen · 335 lines · 65 tokens per session scan A 1f754f5940e0

Subscribe to this mod's changes

security-reviewer is an agent published in the GitHub repository Dannykkh/skill-olympus (5 stars, last pushed 4d ago), licensed MIT. It adds 65 tokens to every session and 4,300 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

document-steward

GOAL: One document per domain. Minimum tokens for maximum clarity.

rwliebs/Dossier · 21 tokens

strategy-fidelity-voc

Evaluates app fidelity and completion against docs/SYSTEMARCHITECTURE.md and domain references. Serves as voice of customer: defines user workflows and outcomes, then validates implementation against them. Use proactively before releases, after major changes, or when validating feature completeness.

rwliebs/Dossier · 0 tokens

cross-project-memory

Designs and executes efficient cross-project and long-term memory so agents build apps better. Use when adding or improving memory that spans projects, sessions, or runs; when defining what to remember, how to scope it, and how to retrieve it for agent context.

rwliebs/Dossier · 56 tokens

architect

Software architecture lead for hybrid systems using traditional architecture (Next.js + PostgreSQL) and AI-agent-supportive architecture (ruvector). Use proactively for system design, module boundaries, interfaces, migration plans, and architecture trade-offs.

rwliebs/Dossier · 47 tokens

investigator

investigates a bug to identify root cause and set success criteria for resolution; creates investigation report for fixer agent to guide implementation.

rwliebs/Dossier · 28 tokens

ai-advocate

Audits the project for poor AI agent behaviors and recommends concrete improvements to make coding workflows more agent-friendly, reliable, and fast. Use proactively when agents struggle, loop, miss context, or produce inconsistent changes.

rwliebs/Dossier · 47 tokens