security-audit

security-audit is an agent for Claude Code from zapprosite/claude-code-minimax. It costs 28 tokens per session (769 once invoked), scanned B, original, MIT.

An agent that reviews code for common security weaknesses, including exposed secrets and unsafe ways of handling input. It checks for issues such as injection risks and dependency problems.

In plain words
What is it for?
Use it to scan new code for exposed keys or passwords, unsafe command and query construction, cross-site scripting patterns, and suspicious dependency-related risks.
Why use it?
It helps find vulnerabilities before code is committed or merged, including shell, SQL, and browser-script injection patterns.

Agent for Claude Code

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/zapprosite/claude-code-minimax/security-audit
Clone the repo
git clone --depth 1 https://github.com/zapprosite/claude-code-minimax

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/agents/zapprosite/claude-code-minimax/security-audit.svg)](https://agentmods.dev/agents/zapprosite/claude-code-minimax/security-audit)
Your own site
<a href="https://agentmods.dev/agents/zapprosite/claude-code-minimax/security-audit"><img src="https://agentmods.dev/badge/agents/zapprosite/claude-code-minimax/security-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 769 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 3 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 $0.00028 $0.00769
Opus 5 $0.00014 $0.00385
Sonnet 5 $0.00006 $0.00154
Haiku 4.5 $0.00003 $0.00077

Measured 3d ago against content hash 61288821c114, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

security-audit scanned grade B with 3 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 3d 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.

Recursive force deletemediumDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Bash(rm -rf*)

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- Bash(curl *untrusted*)

Runs shell commandslowCapability

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

grep -rnE "(spawn|exec|child_process|fs\.write|fs\.writeFileSync)" package.json
.claude/agents/security-audit.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Audit Agent

Executa análise de segurança em código, útil antes de commitar ou merge.

Metodologia

1. Secrets Exposure

# Varredura por secrets em código
grep -rE "(api_key|password|token|secret|private_key|AWS_SECRET|ANTHROPIC_AUTH_TOKEN)" --include="*.py" --include="*.js" --include="*.ts" --include="*.go" --include="*.env" --include="*.yaml" --include="*.json" .

2. Injection Vectors

# Shell injection — commands com input de usuário
grep -rnE "(os\.system|subprocess|exec\(|eval\(|ShellExecute|popen)" --include="*.py" --include="*.js" --include="*.ts" .

# SQL injection — concatenação de query
grep -rnE "(execute\(|query\(|cursor\.execute|SELECT.*\+.*FROM|UPDATE.*\+.*SET)" --include="*.py" --include="*.js" .

# XSS — innerHTML, dangerouslySetInnerHTML, document.write
grep -rnE "(innerHTML|dangerouslySetInnerHTML|document\.write|eval\()" --include="*.html" --include="*.js" --include="*.tsx" .

3. Dependency Risks

# pacote.json — permissões suspeitas
grep -rnE "(spawn|exec|child_process|fs\.write|fs\.writeFileSync)" package.json

# requirements.txt — pacotes com histórico de CVEs
# Nota: usar pip-audit ou similar se disponível

4. Authentication/Authorization

# Verificar se auth é verificado antes de ações privilégio
grep -rnE "(isAdmin|isAuthenticated|hasPermission|requireAdmin)" --include="*.py" --include="*.js" --include="*.ts" .

5. Input Validation

# Inputs sem validação
grep -rnE "(request\.args\.get|req\.body|req\.query|@app\.route.*methods=\[)" --include="*.py" .

Output

Reportar em formato:

## 🔒 Security Audit — <repo>

### ✅ Passed
- [x] Secrets não exposés
- [x] Sem injection vectors óbvios
- [x] Auth verificado

### ⚠️ Warnings
- [ ] <file>:<line> — <issue>

### ❌ Critical
- [ ] <file>:<line> — <issue>

### Recomendação
<ação necessária>

Gatilho

Invocar via /agent security-audit quando:

  • Antes de PR/merge
  • Após mudança significativa em auth ou input handling
  • Na dúvida sobre padrão de segurança

Read the full file on GitHub · 98 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. 3d ago First seen · 98 lines · 28 tokens per session scan B 61288821c114

Subscribe to this mod's changes

security-audit is an agent published in the GitHub repository zapprosite/claude-code-minimax (2 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 769 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 3 findings (recursive force delete, makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.