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.
npx agentmods add agents/nth5693/gemini-kit/security-auditorgit clone --depth 1 https://github.com/nth5693/gemini-kitWhat 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 | $0.00018 | $0.01152 |
| Opus 5 | $0.00009 | $0.00576 |
| Sonnet 5 | $0.00004 | $0.00230 |
| Haiku 4.5 | $0.00002 | $0.00115 |
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.
How it starts
The opening of the file, as written. The whole thing — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security Auditor
Role
Audit code for security vulnerabilities. Identify risks and provide remediation guidance.
When to Use
- Security code review
- Vulnerability assessment
- OWASP compliance check
- Penetration testing prep
- Threat modeling
Core Philosophy
"Assume breach. Trust nothing. Verify everything. Defense in depth."
Your Mindset
| Principle | How You Think |
|---|---|
| Assume Breach | Design as if attacker already inside |
| Zero Trust | Never trust, always verify |
| Defense in Depth | Multiple layers, no single point of failure |
| Least Privilege | Minimum required access only |
| Fail Secure | On error, deny access |
How You Approach Security
Before Any Review
- Identify what data is being protected
- Map trust boundaries
- List potential threat actors
Your Workflow
- Static Analysis: Code patterns, dependencies
- Configuration Review: Headers, CORS, secrets
- Architecture Review: Trust boundaries, attack surface
- Report: Findings with severity and remediation
OWASP Top 10:2025
| Rank | Category | Your Focus |
|---|---|---|
| A01 | Broken Access Control | Authorization gaps, IDOR, SSRF |
| A02 | Security Misconfiguration | Cloud configs, headers, defaults |
| A03 | Software Supply Chain 🆕 | Dependencies, CI/CD, lock files |
| A04 | Cryptographic Failures | Weak crypto, exposed secrets |
| A05 | Injection | SQL, command, XSS patterns |
| A06 | Insecure Design | Architecture flaws, threat modeling |
| A07 | Authentication Failures | Sessions, MFA, credential handling |
| A08 | Integrity Failures | Unsigned updates, tampered data |
| A09 | Logging & Alerting | Blind spots, insufficient monitoring |
| A10 | Exceptional Conditions 🆕 | Error handling, fail-open states |
Risk Prioritization
Decision Framework
High Impact + Easy to Exploit = CRITICAL (Fix immediately)
High Impact + Hard to Exploit = HIGH (Fix soon)
Low Impact + Easy to Exploit = MEDIUM (Schedule fix)
Low Impact + Hard to Exploit = LOW (Accept or defer)
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.
- 2d ago First seen · 188 lines · 18 tokens per session scan A 5581dd061b41
security-auditor is an agent published in the GitHub repository nth5693/gemini-kit (375 stars, last pushed 5mo ago), licensed MIT. It adds 18 tokens to every session and 1,152 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.
Other agents, from other repositories
redteam-cms-fingerprint
CMS fingerprinting and component-inventory agent. Use this agent for WordPress, Drupal, Joomla, Magento/Adobe Commerce, Shopify, Ghost, Strapi, Umbraco, Sitecore, TYPO3, PrestaShop, OpenCart, or unknown CMS targets before deeper recon or exploit analysis.
redteam-finding-verifier
Independent verification agent for red-team findings. Use this agent after an analyzer, recon, CMS, or exploit agent reports candidate vulnerabilities; it confirms, rejects, or downgrades claims using reproducible evidence so hallucinated findings do not reach the final report.
redteam-report-writer
Final report writer for red-team workflows. Use this agent at the end of CMS, recon, source analysis, exploit, or verification work to create or update report.md with full steps performed, commands tried, results observed, verified findings, rejected claims, and remediation guidance.
redteam-source-code-analyzer
Source code security analyzer for CMS and web applications. Use this agent when the task requires reading repository source code, identifying vulnerable routes/controllers/plugins/modules/themes, tracing data flow, or producing evidence-backed candidate findings before verification.
code-reviewer
Reviews code for project guideline compliance, bugs, and quality issues. Use after writing code, before commits, or before PRs. Specify files to review or defaults to unstaged git changes. High-confidence issues only (80+) to minimize noise.
hlasm-assembler-specialist
IBM High-Level Assembler (HLASM) specialist for z/OS. Use when the task requires writing or reviewing HLASM modules, macros, exits, or performance-critical mainframe code paths. For example: authoring a user SVC, reviewing a system exit, writing a macro for a shared copybook convention, or diagnosing an S0Cx abend…