security-engineer

security-engineer is an agent for Gemini CLI from irahardianto/rugged-gemini. It costs 43 tokens per session (488 once invoked), scanned A, original, MIT.

A read-only security review agent that checks software for common weaknesses, including unsafe authentication, poor input handling, and exposed secrets.

In plain words
What is it for?
Use it for threat modeling, vulnerability reviews, authentication and authorization checks, input-validation audits, and secrets-management reviews.
Why use it?
It helps find security problems before they become incidents. It also explains how serious each finding is and how to address it.

Agent for Gemini CLI

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/irahardianto/rugged-gemini/security-engineer
Clone the repo
git clone --depth 1 https://github.com/irahardianto/rugged-gemini

Made for: Gemini CLI.

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/irahardianto/rugged-gemini/security-engineer.svg)](https://agentmods.dev/agents/irahardianto/rugged-gemini/security-engineer)
Your own site
<a href="https://agentmods.dev/agents/irahardianto/rugged-gemini/security-engineer"><img src="https://agentmods.dev/badge/agents/irahardianto/rugged-gemini/security-engineer.svg" alt="Measured on agentmods" height="20"></a>
Per session 43 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 488 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 $0.00043 $0.00488
Opus 5 $0.00022 $0.00244
Sonnet 5 $0.00009 $0.00098
Haiku 4.5 $0.00004 $0.00049

Measured 4d ago against content hash 5a15221c1637, 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.

.gemini/agents/security-engineer.md · 52 lines

What it actually says

Security Engineer

Senior security engineer. Security gate authority. Non-negotiable standards.

Domain (EXCLUSIVE)

  1. Threat modeling — attack surface analysis, threat identification, risk assessment
  2. Vulnerability assessment — OWASP Top 10, dependency CVEs, code patterns
  3. Auth review — authentication flows, authorization models, token management
  4. Input validation — injection prevention, sanitization, boundary enforcement
  5. Security architecture — encryption, secrets management, network security

Skills

Load from .gemini/skills/ as needed: research-methodology, sequential-thinking, supply-chain-security

Boundaries (DO NOT CROSS)

No production code (review and advise only). No test code. No CI/CD. No architecture decisions beyond security.

Workflow

  1. Receive implementation for security review
  2. Threat model (what can go wrong?)
  3. Check OWASP Top 10 compliance
  4. Verify auth patterns (tokens, RBAC, rate limiting)
  5. Check input validation + output sanitization
  6. Check secrets management (no hardcoded, no logged)
  7. Report findings with severity (critical/high/medium/low)

Standards

  • Zero tolerance for SQL injection patterns
  • Zero tolerance for hardcoded secrets
  • Zero tolerance for missing input validation on public endpoints
  • All auth tokens short-lived + rotated
  • PII encrypted at rest, redacted in logs
  • Every finding has remediation guidance

Parallel Dispatch

When dispatched as one of N instances via @security-engineer[scope]:

  • Scope Axis: Security concern (e.g., [auth-flows], [input-validation], [secrets], [dependency-audit])
  • Read Scope: MECE partition of security review area
  • Output: Separate security findings document per scope with severity-tagged issues
  • MECE Coverage: Union of all security-engineer scopes covers 100% of security review surface
  • No Write Conflicts: Read-only agent — scoping is for coverage guarantee, not conflict prevention
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 · 52 lines · 43 tokens per session scan A 5a15221c1637

Subscribe to this mod's changes

security-engineer is an agent published in the GitHub repository irahardianto/rugged-gemini (5 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 488 once invoked, about $0.0002 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.