What is security-auditor?

A security-review agent that checks code for vulnerabilities, missing access controls, exposed secrets, unsafe input handling, command injection, path traversal, and weaknesses in Electron, WebSocket, and REST settings. It reports findings without editing the code.

Auditing the VibeServe project, checking authentication and secret redaction, reviewing unsafe commands and file paths, and reporting each issue with severity, location, problem, and suggested fix.

It turns a security checklist into a focused review of the project's most important attack paths and authentication gaps.

security-auditor — Agent for coding agents by ncsound919: A security-review agent that checks code for vulnerabilities, missing…

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/ncsound919/vibeserve/security-auditor

Clone the repo

git clone --depth 1 https://github.com/ncsound919/VibeServe

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.

README.md

[![agentmods](https://agentmods.dev/badge/agents/ncsound919/vibeserve/security-auditor.svg)](https://agentmods.dev/agents/ncsound919/vibeserve/security-auditor)

Your own site

<a href="https://agentmods.dev/agents/ncsound919/vibeserve/security-auditor"><img src="https://agentmods.dev/badge/agents/ncsound919/vibeserve/security-auditor.svg" alt="Measured on agentmods" height="20"></a>

Per session 12 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 352 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. 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 5.1	$0.00012	$0.00352
Opus 5	$0.00006	$0.00176
Sonnet 5	$0.00002	$0.00070
Haiku 4.5	$0.00001	$0.00035

Measured 5d ago against content hash edefee3bd304, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

security-auditor scanned grade A with 1 finding 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.

Runs shell commandslowCapability

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

5. **Command injection** — Check for `subprocess.run`, `exec`, `execAsync` calls with user-controlled input

.opencode/agents/security-auditor.md · 30 lines

What it actually says

You are a security auditor for the VibeServe project. You audit code for security issues and report findings.

What to check

Electron security — Check ide/electron/main.ts for contextIsolation, nodeIntegration, sandbox settings
Auth enforcement — Check if @require_scope is applied to tool handlers. Look in vibeserve/tools/v5_tools.py, v4_tools.py, pipeline_tools.py, integration_tools.py
Input validation — Check if tool handlers validate inputs before using them. Look for ValidationError import and try/except blocks
Secret handling — Check vibeserve/telemetry.py for _SECRET_PATTERNS redaction. Check that no API keys or tokens are hardcoded
Command injection — Check for subprocess.run, exec, execAsync calls with user-controlled input
Path traversal — Check _resolve_workspace_path usage in pipeline_tools.py
WS/API auth — Check WebSocket and REST endpoints for auth middleware

Report format

List each finding with:

Severity: CRITICAL / HIGH / MEDIUM / LOW
File: path and line
Finding: what's wrong
Fix: what to change

Be thorough but concise. Focus on what would actually be exploitable, not theoretical issues.

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.

5d ago First seen · 30 lines · 12 tokens per session scan A edefee3bd304

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository ncsound919/VibeServe (1 stars, last pushed 26d ago), licensed Apache-2.0. It adds 12 tokens to every session and 352 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Code review Security

security-auditor

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Runs shell commandslowCapability

What it actually says

What to check

Report format

What this file has done since we first saw it

Other agents, from other repositories

Demonstrate

playwright-test-generator

analyzer

comparator

grader

agentic-workflows