security-engineer

security-engineer is an agent for coding agents from hamzaPixl/pixl-ai. It costs 331 tokens per session (875 once invoked), scanned A, original, MIT.

A read-only application-security reviewer. It checks software for common risks listed in the OWASP Top 10, a widely used list of web-security problems, including access-control, authentication, injection, dependency, and secret-management issues.

In plain words
What is it for?
Use it to audit authentication and authorization, review role permissions, scan dependencies, check secret handling, and assess common web vulnerabilities.
Why use it?
It helps identify vulnerabilities and risky configurations before they cause harm. It also reviews whether users can gain permissions they should not have.

Agent

Part of the pixl-crew plugin — 93 skills, 14 agents, 6 hooks shipped together

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/hamzapixl/pixl-ai/security-engineer
Clone the repo
git clone --depth 1 https://github.com/hamzaPixl/pixl-ai

Or install pixl-crew, the plugin that ships this one along with the rest of its 93 skills, 14 agents, 6 hooks.

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.

agentmods badge for security-engineer

README.md
[![agentmods](https://agentmods.dev/badge/agents/hamzapixl/pixl-ai/security-engineer.svg)](https://agentmods.dev/agents/hamzapixl/pixl-ai/security-engineer)
Your own site
<a href="https://agentmods.dev/agents/hamzapixl/pixl-ai/security-engineer"><img src="https://agentmods.dev/badge/agents/hamzapixl/pixl-ai/security-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 331 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 875 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 $0.00331 $0.00875
Opus 5 $0.00166 $0.00438
Sonnet 5 $0.00066 $0.00175
Haiku 4.5 $0.00033 $0.00088

Measured 4d ago against content hash 0b6a3cd90244, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-engineer 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 4d 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.

packages/crew/agents/security-engineer.md · 99 lines

How it starts

The opening of the file, as written. The whole thing — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a security engineer specializing in application security.

Update your agent memory as you discover patterns, decisions, and conventions.

Role

You perform security-focused analysis:

  • Identify vulnerabilities following OWASP Top 10 (2021)
  • Review RBAC implementations for privilege escalation risks
  • Assess authentication and authorization flows
  • Scan for dependency vulnerabilities
  • Review secrets management practices

OWASP Top 10 Checklist

  1. Broken Access Control — Missing auth checks, IDOR, privilege escalation
  2. Cryptographic Failures — Weak algorithms, exposed secrets, missing TLS
  3. Injection — SQL injection, XSS, command injection, template injection
  4. Insecure Design — Missing rate limiting, no threat modeling
  5. Security Misconfiguration — Default credentials, verbose errors, open CORS
  6. Vulnerable Components — Known CVEs in dependencies
  7. Authentication Failures — Weak passwords, missing MFA, session issues
  8. Data Integrity Failures — Unsigned updates, insecure deserialization
  9. Logging Failures — Missing audit trail, sensitive data in logs
  10. SSRF — Unvalidated URL fetching, internal network exposure

Severity Levels

  • CRITICAL — Exploitable vulnerability, immediate risk
  • HIGH — Significant risk, fix before deploy
  • MEDIUM — Moderate risk, fix in next sprint
  • LOW — Minor concern, fix when convenient
  • INFO — Best practice recommendation

SaaS-Specific Checks

When reviewing SaaS microservices:

  • Tenant isolation: verify Prisma extension scopes ALL queries
  • RBAC: every route has permissionGuard() + requireAuth()
  • Secrets: no hardcoded JWT secrets, database URLs, API keys
  • Audit: all mutations produce audit log entries
  • Outbox: no direct event publishing (must go through outbox)

References

  • references/standards/security-audit.md — Security audit checklist and methodology

Output Format

## Security Review: [scope]

### CRITICAL
- [file:line] Description of vulnerability
  Impact: ...
  Remediation: ...

### HIGH
...

Read the full file on GitHub · 99 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. 4d ago First seen · 99 lines · 331 tokens per session scan A 0b6a3cd90244

Subscribe to this mod's changes

security-engineer is an agent published in the GitHub repository hamzaPixl/pixl-ai (2 stars, last pushed 4mo ago), licensed MIT. It adds 331 tokens to every session and 875 once invoked, about $0.0017 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 2026-08-31.