agentmods.dev

security-and-hardening

security-and-hardening is a skill for Claude Code, Codex from vignesh2027/AI-AGENT-SKILLS. It costs 19 tokens per session (926 once invoked), scanned A, original, MIT.

A security review process for code and infrastructure. It looks at how attackers could misuse changes, including problems with input, secrets, permissions, dependencies, and exposed services.

In plain words
What is it for?
Threat-modeling changes and hardening authentication, data storage, user input, external APIs, endpoints, forms, infrastructure, and dependencies.
Why use it?
It helps find common security weaknesses before they reach production or become incidents.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 2repo 2mo ago A scan 19 tokens original MIT

Good fit Threat-modeling changes and hardening authentication, data storage, user input, external APIs, endpoints, forms, infrastructure, and dependencies.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/vignesh2027/ai-agent-skills/security-and-hardening
View source ↗ vignesh2027/AI-AGENT-SKILLS
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.

Any agent
npx skills add vignesh2027/AI-AGENT-SKILLS --skill security-and-hardening
Clone the repo
git clone --depth 1 https://github.com/vignesh2027/AI-AGENT-SKILLS

Made for: Claude Code, Codex.

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-and-hardening

README.md
[![agentmods](https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/security-and-hardening/github.svg)](https://agentmods.dev/skills/vignesh2027/ai-agent-skills/security-and-hardening)
Your own site
<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/security-and-hardening"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/security-and-hardening/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for security-and-hardening

Your own site · 80×15
<a href="https://agentmods.dev/skills/vignesh2027/ai-agent-skills/security-and-hardening"><img src="https://agentmods.dev/badge/skills/vignesh2027/ai-agent-skills/security-and-hardening.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 926 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00019 $0.00926
Opus 5.5 $0.00008 $0.00370
Sonnet 5.5 $0.00004 $0.00185
Haiku 4.5 $0.00002 $0.00093

Measured 2mo ago against content hash d111483d9df8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

security-and-hardening 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 2mo 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.

skills/security-and-hardening/SKILL.md · 95 lines

How it starts

The opening of the file, as written. The whole thing — 95 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Overview

Security is not a feature you add — it is a property you maintain. Most security failures are not sophisticated attacks; they are missing input validation, exposed secrets, misconfigured permissions, and unpatched dependencies. This skill systematically eliminates these before they reach production.

When to Use

  • Before merging any PR that touches auth, data storage, user input, or external APIs
  • When adding a new endpoint, form, or data type
  • When setting up or modifying infrastructure
  • As part of the /review workflow

Process

Step 1: Threat model the change

Ask: what can an attacker do with this change? What data does it touch? What systems does it connect to? Who has access? Threat model in 10 minutes with STRIDE:

  • Spoofing — Can someone impersonate a legitimate user?
  • Tampering — Can someone modify data they shouldn't?
  • Repudiation — Can someone deny they took an action?
  • Information Disclosure — Can someone read data they shouldn't?
  • Denial of Service — Can someone block legitimate access?
  • Elevation of Privilege — Can someone gain permissions they shouldn't have?

Step 2: Input validation

  • Validate all inputs at the boundary (before processing or storage)
  • Validate type, length, format, and range
  • Reject invalid inputs — don't sanitize and continue
  • Parameterize all database queries (no string concatenation)
  • Encode all outputs for their context (HTML, SQL, shell, JSON)

Step 3: Authentication and authorization

  • Verify authentication on every request (don't cache auth state across requests)
  • Check authorization on every resource access (not just at the route level)
  • Use principle of least privilege: request only the permissions you need
  • Implement rate limiting on auth endpoints
  • Ensure session tokens are invalidated on logout

Step 4: Secrets management

  • No secrets in code, commits, or logs
  • Use environment variables or a secrets manager
  • Rotate secrets after any exposure (assume exposure if committed to git)
  • Verify: git log --all -p | grep -i "password\|secret\|token\|key" — if anything shows, rotate immediately

Read the full file on GitHub · 95 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. 2mo ago First seen · 95 lines · 19 tokens per session scan A d111483d9df8

Subscribe to this mod's changes

security-and-hardening is a skill published in the GitHub repository vignesh2027/AI-AGENT-SKILLS (2 stars, last pushed 2mo ago), licensed MIT. It adds 19 tokens to every session and 926 once invoked, about $0.0001 per session on Opus 5.5. 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.

Claude CodeSecurityagent-skillsai-agentscoding-agentcursor-aideveloper-tools
Related

security-and-hardening compared with skills from other repositories

security-and-hardening next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
security-and-hardeningvignesh2027/AI-AGENT-SKILLSSkill22mo agoMITA19Claude Code, Codex
cw-gatesHmbown/CodewhaleSkill41k1mo agoMITA48Claude Code, Codex
feishuHmbown/CodeWhaleSkill41k6d agoMITA33Claude Code, Codex
eval-dataset-designbojieli/ai-agent-bookSkill57k1mo agoApache-2.0A138Claude Code, Codex
memory-systembojieli/ai-agent-bookSkill57k1mo agoApache-2.0A95Claude Code, Codex
release-helperSahir619/fable-methodSkill2.3k1mo agoMITA43Claude Code
loongsuite-pilot-insightalibaba/loongsuite-pilotSkill242yesterdayApache-2.0A111Claude Code, Codex