Chalk Labs
Need help deploying security-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/sd0xdev-security-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents, testing, security, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/security-review
Tools it pre-approves 6
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(git:*),Read,Grep,Glob,Bash(node:*),Write
What's inside
- Skill name
security-review- Description
- Security review via Codex exec. Use when: OWASP Top 10:2025 audit, dependency vulnerability check, security-sensitive changes. Not for: code review (use codex-code-review), test review (use test-review). Output: security findings + audit report.
- License
- MIT
- Allowed tools
- Bash(git:*),, Read,, Grep,, Glob,, Bash(node:*),, Write
- Instructions
- 105 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (3)
- SKILL.md
- codex-prompt-security.md · references/
- examples.md · references/
SKILL.md (first lines)
# Security Review Skill
## Trigger
- Keywords: security review, OWASP, vulnerability, dep-audit, npm audit, dependency security
## When NOT to Use
- General code review (use `codex-code-review`)
- Functional testing (use `test-review`)
- Performance issues (not security-related)
## Commands
| Command | Purpose | When |
| ----------------- | ------------------------ | ----------------------- |
| `/codex-security` | OWASP Top 10 audit | Security-sensitive code |
| `/dep-audit` | Dependency security audit | Periodic / PR |
## Workflow: `/codex-security`
```
Determine scope → Collect changes → Codex OWASP review → Findings + Gate → Loop if Must fix
```
### Step 1: Determine Scope
Parse `--scope` from arguments, default to `src/`.
### Step 2: Collect Change **Metadata**
Metadata, not content: the first dispatch carries the changed-file list and diff stats, and Codex
reads the diffs itself from the sandbox (`@rules/codex-invocation.md` § Required in every first-dispatch prompt). A truncated
`| head -1500` excerpt was the old shape, and it decided for the reviewer which 1500 lines of a
security review mattered.
1. `CHANGED_FILES`: `git diff --name-only HEAD -- <scope>` ∪ `git ls-files --others --exclude-standard -- <scope>`
2. `DIFF_STAT`: `git diff --stat HEAD -- <scope>`
3. `SCOPE`: the resolved scope argument, plus the security-relevant paths a
`Glob("**/*{auth,login,password,token,secret,key,credential}*")` surfaces — named as places to
look, never pasted
### Step 3: Codex Security Review
**First review**: dispatch per `@skills/codex-code-review/references/codex-transport.md` § Start with the OWASP prompt. See `references/codex-prompt-security.md`.
**Save the returned `threadId`.**
**Loop review**: dispatch per `@skills/codex-code-review/references/codex-transport.md` § Resume with the re-review template. See `references/codex-prompt-security.md`.
### Step 4: Consolidate Output
Organize results into findings summary table + detailed findings + gate.
## OWASP Top 10:2025
The version is part of the identifier: SSRF is no longer A10 (it sits inside A01), and A02–A06
renumbered, so a finding labelled with a 2021 code says something different to whoever reads it.
| Code | Category | Check Focus |
| ---- | ----------------------- | ---------------------------------------- |
| A01 | Broken Access Ctrl | IDOR, permission bypass, CORS, **SSRF** |
| A02 | Misconfiguration | Debug mode, default passwords |
| A03 | Supply Chain Failures | Vulnerable deps, unverified build sources |
| A04 | Crypto Failures | Sensitive data encryption, weak crypto |
| A05 | Injection | SQL/NoSQL/Cmd Injection, XSS |
| A06 | Insecure Design | Rate Limiting, business logic |
| A07 | Auth Failures | Brute force, session, weak passwords |
| A08 | Integrity Failures | Deserialization, CI/CD |
| A09 | Logging & Alerting | Sensitive data in logs, auditing, alerts |
| A10 | Exceptional Conditions | Error paths that fail open or leak |
## Review Loop
**⚠️ @CLAUDE.md auto-loop: fix → re-review → ... → ✅ PASS ⚠️**
⛔ Must fix → fix P0 issues → `/codex-security --continue <threadId>` → repeat until ✅ Mergeable.
Max 3 rounds. Still failing → report blocker.
## Verification
- [ ] Each issue tagged with severity (P0/P1/P2)
- [ ] Gate is explicit (✅ Mergeable / ⛔ Must fix)
- [ ] Fix recommendations are specific and actionable
- [ ] Includes verification test method
- [ ] Codex independently researched auth/input/sensitive code
## References
- OWASP prompt: `references/codex-prompt-security.md`
- Examples: `references/examples.md`
- Standards: @rules/security.md
## Examples
```
Input: /codex-security --scope src/controller/
Action: OWASP Top 10 check → output issues + Gate
Input: /dep-audit --level high
Action: npm audit → filter high/critical → output report
```From sd0xdev/sd0x-harness, MIT.
More from sd0xdev/sd0x-harness
- 0.713score
debug
sd0xdev
Interactive debugging workflow with hypothesis-driven probe loop.
SkillAFreshness: A★ 194Claude Code - 0.713score
contract-decode
sd0xdev
EVM contract error and calldata decoder.
SkillAFreshness: A★ 194Claude Code - 0.713score
codex-brainstorm
sd0xdev
Adversarial brainstorming via Claude+Codex debate.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
best-practices
sd0xdev
Industry best practices conformance audit with mandatory adversarial debate.
SkillAFreshness: A★ 194Claude Code - 0.713score
codex-cli-review
sd0xdev
Code review via Codex CLI with full disk access.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
codex-explain
sd0xdev
Explain complex code via Codex exec.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
ask
sd0xdev
Context-aware Q&A with auto context gathering.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
claude-health
sd0xdev
Claude Code config health check + plugin sync.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
code-explore
sd0xdev
Pure Claude code investigation.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
code-investigate
sd0xdev
Dual-perspective code investigation.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
codex-architect
sd0xdev
Codex architecture consulting.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
deep-explore
sd0xdev
Multi-wave parallel code exploration orchestrator.
SkillAFreshness: A★ 194Claude Code +9
Signals
- Stars
- 194
- Forks
- 26
- Open issues
- 5
- Last commit (this folder)
- Sep 5, 2026 (2 months ago)
- Last release
- Oct 6, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/sd0xdev/sd0x-harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from sd0xdev
- 0.713score
code-investigate
sd0xdev
Dual-perspective code investigation.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
code-explore
sd0xdev
Pure Claude code investigation.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
ask
sd0xdev
Context-aware Q&A with auto context gathering.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
best-practices
sd0xdev
Industry best practices conformance audit with mandatory adversarial debate.
SkillAFreshness: A★ 194Claude Code - 0.713score
claude-health
sd0xdev
Claude Code config health check + plugin sync.
SkillAFreshness: A★ 194Claude Code +9 - 0.713score
codex-architect
sd0xdev
Codex architecture consulting.
SkillAFreshness: A★ 194Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get security-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
security-review skill. Agent Mart. https://agentmart.dev/skills/sd0xdev-security-review (last updated 2026-10-24)