Borrowing it
Nothing to install: this file belongs to talayash/agentrium. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/talayash/agentrium/master/.claude/agents/security-reviewer.mdgit clone --depth 1 https://github.com/talayash/agentriumWrote 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/agents/talayash/agentrium/security-reviewer)<a href="https://agentmods.dev/agents/talayash/agentrium/security-reviewer"><img src="https://agentmods.dev/badge/agents/talayash/agentrium/security-reviewer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/agents/talayash/agentrium/security-reviewer"><img src="https://agentmods.dev/badge/agents/talayash/agentrium/security-reviewer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00000 | $0.00586 |
| Opus 5.5 | $0.00000 | $0.00234 |
| Sonnet 5.5 | $0.00000 | $0.00117 |
| Haiku 4.5 | $0.00000 | $0.00059 |
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 1mo 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 — 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 Agentrium - a Tauri 2.x desktop app that spawns Claude Code CLI processes via PTY.
Threat Model
Agentrium has a unique threat surface:
- PTY command injection: User input flows through xterm.js → IPC → PTY. Malicious input could escape the Claude Code session
- IPC boundary: Frontend-to-backend commands must validate all parameters
- Process spawning:
cmd /Cwrapping on Windows - ensure proper escaping - File system access: Workspace paths from user input used in file operations
- Auto-updater: Signed updates from GitHub - verify signing chain
- 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
- Search for dangerous patterns:
cmd /Cwith user-controlled strings- Raw SQL queries (should use parameterized)
eval(),innerHTML,dangerouslySetInnerHTML- Hardcoded paths, credentials, tokens
- Check Tauri capabilities in
src-tauri/capabilities/default.json - Review CSP in
src-tauri/tauri.conf.json - 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
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.
- 1mo ago Changed 244629299c3a
- 1mo ago First seen · 75 lines · 0 tokens per session scan A 94ae48836c5b
security-reviewer is an agent published in the GitHub repository talayash/agentrium (46 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.
Other agents, from other repositories
code-reviewer
Reviews completed implementation for governing-source compliance, scope economy, repository quality policy, and material code correctness. Use after implementation or when review/implementation check/compliance is requested.
code-verifier
Verifies repository-backed claims and implementation feasibility in PRDs, Design Docs, or Work Plans. Use before document review, after implementation, or for reverse-engineered artifact verification.
legal
General Counsel who runs the six-skill legal department, finds the path to yes, and keeps deals moving without signing away the company. Use PROACTIVELY for any legal-adjacent task: contract review, NDA triage, compliance checks, risk assessment, vendor vetting, signature routing. MUST BE USED when a contract or NDA…
sales
VP of Sales of Claude, Inc., commanding 6 revenue skills — account research, cold outreach, call prep, proposals, objection handling, pipeline review. Use PROACTIVELY for any prospecting, outreach, deal, quote, negotiation or pipeline task. MUST BE USED when the user wants to research a prospect, write a cold email…
Explore
Read-only search agent for broad fan-out searches, when answering means sweeping many files, directories or naming conventions and you only need the conclusion, not the file dumps. It reads excerpts rather than whole files, so it locates code; it does not review or audit it. Specify search breadth: quick for one…
satd-analyst
Analyzes self-admitted technical debt markers (TODO, FIXME, HACK) to prioritize cleanup.