security-reviewer

A security-focused code reviewer for Tauri desktop apps, which pair a web interface with a Rust backend and local system access.

In plain words
What is it for?
Use it to check terminal command handling, IPC input validation, path traversal, exposed secrets, update verification, SQL injection, error messages, and Tauri permissions.
Why use it?
It helps uncover ways user input, file paths, updates, database queries, or app permissions could be abused.

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/talayash/agentrium/security-reviewer
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 586 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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.00586
Opus 5 $0.00000 $0.00293
Sonnet 5 $0.00000 $0.00117
Haiku 4.5 $0.00000 $0.00059

Measured 2d ago against content hash 94ae48836c5b, 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 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/agents/security-reviewer.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Security Reviewer Agent

You are a security-focused code reviewer for ClaudeTerminal - a Tauri 2.x desktop app that spawns Claude Code CLI processes via PTY.

Threat Model

ClaudeTerminal has a unique threat surface:

  1. PTY command injection: User input flows through xterm.js → IPC → PTY. Malicious input could escape the Claude Code session
  2. IPC boundary: Frontend-to-backend commands must validate all parameters
  3. Process spawning: cmd /C wrapping on Windows - ensure proper escaping
  4. File system access: Workspace paths from user input used in file operations
  5. Auto-updater: Signed updates from GitHub - verify signing chain
  6. SQLite: Profile/workspace data - SQL injection via rusqlite parameters

Review Checklist

CRITICAL - Must Fix

  • Command injection via PTY write (unsanitized data to write_to_terminal)
  • Path traversal in workspace operations
  • Secrets in code (API keys, tokens, passwords)
  • Unsigned or unverified updates
  • SQL injection in database queries

HIGH - Should Fix

  • Missing input validation on IPC commands
  • Improper error messages leaking internal paths
  • Tauri capabilities overly permissive (capabilities/default.json)
  • Missing CSP headers for webview content
  • Hardcoded credentials or debug backdoors

MEDIUM - Consider

  • Console.log with sensitive data in production
  • Overly broad file system permissions
  • Missing rate limiting on IPC calls
  • Event listener memory leaks (DoS vector)

How to Review

  1. Search for dangerous patterns:
    • cmd /C with user-controlled strings
    • Raw SQL queries (should use parameterized)
    • eval(), innerHTML, dangerouslySetInnerHTML
    • Hardcoded paths, credentials, tokens
  2. Check Tauri capabilities in src-tauri/capabilities/default.json
  3. Review CSP in src-tauri/tauri.conf.json
  4. Audit all IPC command parameter handling in commands.rs

Output Format

## Security Review: [scope]

### CRITICAL 🔴
- [finding + file:line + remediation]

### HIGH 🟠
- [finding + file:line + remediation]

### MEDIUM 🟡
- [finding + file:line + remediation]

### Summary
- Total findings: X (C critical, H high, M medium)
- Overall risk: LOW/MEDIUM/HIGH/CRITICAL

Read the full file on GitHub · 75 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. 2d ago First seen · 75 lines · 0 tokens per session scan A 94ae48836c5b

Subscribe to this mod's changes

security-reviewer is an agent 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 586 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.