What is security-review?

A security-audit command that reviews a codebase or recent changes for common application-security problems. It covers command injection, unsafe file paths, exposed secrets, overly broad permissions, dependency vulnerabilities, and unsafe frontend code.

Use it to audit process spawning, path handling, secret storage, Tauri permissions, input validation, error messages, dependencies, and frontend uses of functions such as eval or innerHTML.

It helps identify ways attackers or accidental inputs could run commands, access unintended files, expose credentials, abuse backend interfaces, or exploit vulnerable packages.

security-review — Command by talayash

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 commands/talayash/agentrium/security-review

Clone the repo

git clone --depth 1 https://github.com/talayash/agentrium

Made for: Claude Code.

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 445 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 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.

Model	Per session	Once invoked
Fable 5	$0.00000	$0.00445
Opus 5	$0.00000	$0.00222
Sonnet 5	$0.00000	$0.00089
Haiku 4.5	$0.00000	$0.00044

Measured 2d ago against content hash 8402933e0d20, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-review 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 2d 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.

.claude/commands/security-review.md · 66 lines

What it actually says

Security Review

Run a security audit on the codebase or recent changes.

Instructions

Perform a security review of: $ARGUMENTS (or entire codebase if no arguments)

Scan Areas

1. Command Injection

Search src-tauri/src/ for cmd /C, Command::new, process spawning
Verify all user-controlled strings are properly escaped
Check write_to_terminal for injection vectors

2. Path Traversal

Search for file operations using user-provided paths
Check workspace loading/saving for path validation
Ensure no .. traversal is possible

3. Secrets Detection

Search entire codebase for patterns: API keys, tokens, passwords, secrets
Check .env files, config files, hardcoded strings
Verify .gitignore covers sensitive files

4. IPC Security

Review src-tauri/capabilities/default.json for overly broad permissions
Check that all IPC commands validate their inputs
Verify error messages don't leak internal paths or state

5. Dependency Audit

Check for known vulnerabilities: npm audit and cargo audit (if available)
Flag outdated dependencies with known CVEs

6. Frontend Security

Search for eval(), innerHTML, dangerouslySetInnerHTML
Check CSP configuration in tauri.conf.json
Verify no sensitive data in localStorage (Zustand persist)

7. Update Security

Verify auto-updater uses signed releases
Check update endpoint configuration

Output

## Security Audit Report

### CRITICAL 🔴 (must fix immediately)
[findings]

### HIGH 🟠 (should fix before release)
[findings]

### MEDIUM 🟡 (fix when convenient)
[findings]

### LOW 🔵 (informational)
[findings]

### Summary
- Total: N findings (C critical, H high, M medium, L low)
- Risk level: LOW / MEDIUM / HIGH / CRITICAL
- Recommended actions: [prioritized list]

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.

2d ago First seen · 66 lines · 0 tokens per session scan A 8402933e0d20

Subscribe to this mod's changes

security-review is a command published in the GitHub repository talayash/agentrium (39 stars, last pushed 2d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 445 tokens. 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 2026-08-30.

Code review Frontend Security builders claude-code grid-view profiles vibe-coding

security-review