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.
npx agentmods add skills/orlando-japan/claude-code-setting/security-auditnpx skills add orlando-japan/claude-code-setting --skill security-auditgit clone --depth 1 https://github.com/orlando-japan/claude-code-settingWrote 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.
[](https://agentmods.dev/skills/orlando-japan/claude-code-setting/security-audit)<a href="https://agentmods.dev/skills/orlando-japan/claude-code-setting/security-audit"><img src="https://agentmods.dev/badge/skills/orlando-japan/claude-code-setting/security-audit.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00034 | $0.00943 |
| Opus 5 | $0.00017 | $0.00472 |
| Sonnet 5 | $0.00007 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00094 |
Grade A, and why
security-audit 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.
How it starts
The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security audit
The point is finding exploitable weaknesses. "Could theoretically be bad" isn't an audit finding.
Threat model first
Before looking at code, answer:
- Who can reach this? Internet strangers, authenticated users, internal services?
- Under what auth? Anonymous, session, API token, service-to-service?
- What's the impact of compromise? Read a record, write a record, escalate to admin, exfiltrate the DB, RCE?
The same bug means different things at different reach levels.
Priority order
1. Authentication and authorization
- Is authn separate from authz? Authn = "who are you," authz = "what can you do."
- Is the check on the server, not the UI?
- Can you access another user's resource by changing the ID in the URL (IDOR)?
- Is there a privilege escalation path?
- What happens on missing / expired / malformed tokens?
2. Input handling at trust boundaries
- Injection. Anywhere user input meets an interpreter: SQL, shell, template, HTML, LDAP, NoSQL, XML. Use parameterized APIs.
- Deserialization.
pickle,unserialize,eval, JNDI,yaml.load— any of these on untrusted input is a finding. - Path traversal. File paths built from user input →
../escape. Use allowlists. - SSRF. Server makes HTTP requests to user-supplied URLs → internal network access. Block RFC 1918, 169.254, localhost.
- XXE. XML parsers with external entities enabled.
3. Secrets handling
- Hardcoded secrets in source (grep
secret,password,token,key,api_key). - Secrets in logs (request loggers dumping headers, error loggers dumping objects).
- Secrets in error messages returned to users.
- Secrets in git history (
git log -p | grep ...). - Weak defaults that never get rotated.
4. Crypto and randomness
Math.random()used for anything security-related → finding.- MD5 / SHA1 for integrity or passwords → finding.
- ECB mode, reused IVs, homegrown crypto → finding.
- Missing signature verification on webhooks / tokens.
- Missing TLS cert validation.
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.
- 5d ago First seen · 102 lines · 34 tokens per session scan A e6bf7d014636
security-audit is a skill published in the GitHub repository orlando-japan/claude-code-setting (2 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 943 once invoked, about $0.0002 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.
Other skills, from other repositories
security-guardian
Expert en sécurité applicative pour détecter les vulnérabilités, auditer le code, et guider les bonnes pratiques de sécurité. OWASP Top 10, authentification, autorisation, cryptographie, gestion de secrets. Utiliser pour audits sécurité, reviews de code sensible, conception de features sécurisées, ou résolution de…
security-audit
代码安全审计技能 - 执行OWASP Top 10扫描、密钥检测、依赖审计.
security
Elite cybersecurity expert specializing in zero-day detection, vulnerability assessment, and perimeter defense. Think like an attacker, defend like an expert.
007
Security audit, hardening, threat modeling (STRIDE/PASTA), Red/Blue Team, OWASP checks, code review, incident response, and infrastructure security for any project.
edgeone-clawscan
The first security skill to install after setting up OpenClaw — powered by Tencent Zhuque Lab. Works like an antivirus for your AI environment: audits installed skills, scans skills before installation, and performs a full OpenClaw security health check to prevent data leaks and privacy risks. Backed by Tencent Zhuque…
edgeone skill scanner
Scan any agent skill for security risks before you install or use it. Powered by Tencent Zhuque Lab A.I.G (AI-Infra-Guard). 100% local static analysis — no file contents or credentials leave your device. Compatible with CodeBuddy, Cursor, Windsurf, Claude Code, OpenClaw and more. Triggers on: 这个 skill 安全吗, skill 安全扫描…