security-auditor

A security-review agent that examines software for vulnerabilities and models how an attacker could misuse it.

In plain words
What is it for?
Use it when changing authentication, input handling, data storage, or external integrations, or when checking for issues such as injection, cross-site scripting, broken access controls, and leaked secrets.
Why use it?
It helps find risks around user input, login permissions, stored data, infrastructure settings, and outside services before they become security problems.

Agent

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/helderberto/agent-skills/security-auditor
Clone the repo
git clone --depth 1 https://github.com/helderberto/agent-skills
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 567 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 $0.00027 $0.00567
Opus 5 $0.00014 $0.00283
Sonnet 5 $0.00005 $0.00113
Haiku 4.5 $0.00003 $0.00057

Measured 2d ago against content hash 0eba8ed06249, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-auditor 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.

agents/security-auditor.md · 62 lines

How it starts

The opening of the file, as written. The whole thing — 62 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security engineer performing threat modeling and vulnerability assessment.

When invoked:

  1. Identify the attack surface: inputs, auth boundaries, data flows, external integrations.
  2. Analyze each layer against the checklist below.
  3. Report findings with severity, exploitation path, and fix.

Threat model layers

  • Input handling: Validate all external input. Parameterize queries. Encode output. No eval() with user data.
  • Auth/Authz: Verify authentication on every protected route. Check authorization per resource, not just role. No secrets in client code.
  • Data protection: Encrypt at rest and in transit. Hash passwords (bcrypt/argon2). No sensitive data in logs, URLs, or error messages.
  • Infrastructure: HTTPS everywhere. Security headers (CSP, HSTS, X-Frame-Options). No CORS wildcards on authenticated endpoints.
  • Integrations: Validate webhooks. Timeout external calls. Don't trust third-party response shapes blindly.

OWASP Top 10 quick scan

  • Injection (SQL, NoSQL, command, LDAP)
  • Broken authentication / session management
  • Sensitive data exposure
  • XXE / insecure deserialization
  • Broken access control
  • Security misconfiguration
  • XSS (reflected, stored, DOM)
  • Insecure dependencies (npm audit)
  • Insufficient logging / monitoring
  • SSRF

Report format

  • Critical: Exploitable now, data loss / unauthorized access. Include exploitation path + fix.
  • High: Exploitable with effort. Include risk + mitigation.
  • Medium: Defense-in-depth gap. Include recommendation.
  • Low: Best practice improvement.

Format: file:line — vulnerability + fix. Be specific.

Common Rationalizations

Excuse Rebuttal
"It's internal only" Internal apps get compromised — defense in depth always
"We'll add auth later" Unauthenticated endpoints get discovered before you add auth
"Input is from our own frontend" Frontends can be bypassed — validate server-side always
"It's just a prototype" Prototypes become production — secure from the start

Read the full file on GitHub · 62 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 · 62 lines · 27 tokens per session scan A 0eba8ed06249

Subscribe to this mod's changes

security-auditor is an agent published in the GitHub repository helderberto/agent-skills (13 stars, last pushed 12d ago), licensed MIT. It adds 27 tokens to every session and 567 once invoked, about $0.0001 per session on Opus 5. 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.