security-iac-triage

security-iac-triage is a skill for Claude Code from ch0ks/hackarandas-claude-toolbelt. It costs 168 tokens per session (9,238 once invoked), scanned A, original, MIT.

A security-triage workflow that reviews findings from Semgrep Pro or Claude security-code-review alongside infrastructure-as-code files. Infrastructure as code describes how systems are deployed using files such as Terraform, Kubernetes, or CloudFormation.

In plain words
What is it for?
Use it to inspect deployment facts, choose a conservative or lenient scoring posture, and assign reproducible CVSS 4.0 scores with explanations for each vector.
Why use it?
It helps judge whether a reported vulnerability is actually exposed in the repository's deployment setup, instead of scoring it from code alone.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Good fit Use it to inspect deployment facts, choose a conservative or lenient scoring posture, and assign reproducible CVSS 4.0 scores with explanations for each vector.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ch0ks/hackarandas-claude-toolbelt/security-iac-triage
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 ch0ks/hackarandas-claude-toolbelt --skill security-iac-triage
Clone the repo
git clone --depth 1 https://github.com/ch0ks/hackarandas-claude-toolbelt

Made for: Claude Code.

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-iac-triage

README.md
[![agentmods](https://agentmods.dev/badge/skills/ch0ks/hackarandas-claude-toolbelt/security-iac-triage/github.svg)](https://agentmods.dev/skills/ch0ks/hackarandas-claude-toolbelt/security-iac-triage)
Your own site
<a href="https://agentmods.dev/skills/ch0ks/hackarandas-claude-toolbelt/security-iac-triage"><img src="https://agentmods.dev/badge/skills/ch0ks/hackarandas-claude-toolbelt/security-iac-triage/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-iac-triage

Your own site · 80×15
<a href="https://agentmods.dev/skills/ch0ks/hackarandas-claude-toolbelt/security-iac-triage"><img src="https://agentmods.dev/badge/skills/ch0ks/hackarandas-claude-toolbelt/security-iac-triage.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 168 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 9,238 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 $0.00168 $0.09238
Opus 5 $0.00084 $0.04619
Sonnet 5 $0.00034 $0.01848
Haiku 4.5 $0.00017 $0.00924

Measured 11d ago against content hash 9d27eeb29f04, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

security-iac-triage 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 11d 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-iac-triage/SKILL.md · 797 lines

How it starts

The opening of the file, as written. The whole thing — 797 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Staff Security Engineer performing structured vulnerability triage. Your job is to score each finding using CVSS 4.0, grounding every vector decision in observable facts extracted from the repository's IaC files — not theoretical assumptions. The output must be reproducible: any engineer who reads the same IaC files and your justification should arrive at the same score.


Step 0 — Select Scoring Posture

Before doing anything else, ask the user:

How conservative should the triage scoring be?

  1. Strict    — Every unknown vector is scored worst-case. No benefit of the doubt.
                 Use for: compliance audits, pen-test prep, production hardening.

  2. Standard  — Unknowns are inferred from IaC context (e.g. no public ports found →
                 assume internal access, not internet exposure). Use for: standard
                 sprint security reviews, pre-merge checks.

  3. Lenient   — Absence of evidence is treated as evidence of low risk. Unknowns
                 default to low-impact values. Use for: internal tooling, early-stage
                 projects, developer experience reviews.

Type 1, 2, or 3 (default: 2):

Wait for user input. If the user presses Enter without typing, default to Standard (2).

Store the chosen posture as POSTURE = Strict | Standard | Lenient. This value drives all unknown-vector defaults in Step 2 and is stamped on every triage record and the report header.

Unknown-vector defaults by posture:

Vector Strict Standard Lenient
AV N A L
AC L L H
AT N N P
PR N L H
UI N N P
VC H H L
VI H H L
VA H L N
SC H L N
SI H L N
SA H N N
E P U U

Any vector where IaC evidence IS found overrides the posture default — IaC facts always take precedence over posture defaults.


Step 1 — Load Context

1a. Locate the Security Code Review Report

Read the full file on GitHub · 797 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. 11d ago First seen · 797 lines · 0 tokens per session scan A 9d27eeb29f04

Subscribe to this mod's changes

security-iac-triage is a skill published in the GitHub repository ch0ks/hackarandas-claude-toolbelt (5 stars, last pushed 4mo ago), licensed MIT. It adds 168 tokens to every session and 9,238 once invoked, about $0.0008 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.

Related

Other skills, from other repositories

prompt-master

Generates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other…

nidhinjs/prompt-master · 78 tokens

codeql-expert

Expert-level CodeQL for static analysis, vulnerability detection, and security code scanning. Use when the user mentions static analysis, SAST, vulnerability detection, or github security, or when the task involves writing CodeQL queries, building a CodeQL database, taint tracking, or scanning for injection and…

personamanagmentlayer/pcl · 68 tokens

skill-provenance

Version, validate, package, verify, recover, and hand off Agent Skill bundles across local folders, registries, platform uploads, and agent sessions. Use for MANIFEST.yaml, CHANGELOG.md, bundle hashes, stale evals, frontmatter portability, derived skill packages, or version identity that must survive filename changes…

snapsynapse/skill-provenance · 99 tokens

bootstrap

Add version tracking to an existing unversioned skill bundle. Use when you have a skill project with SKILL.md but no MANIFEST.yaml, no version headers, and no changelog. Creates the initial manifest, adds version metadata to files, and generates the first changelog entry. Triggers on: "bootstrap this skill", "add…

snapsynapse/skill-provenance · 91 tokens

close

Update version tracking when finishing work on a skill bundle. Use when you're done editing a skill project and need to bump version headers, recompute manifest hashes, update the changelog, flag stale files, or prepare a commit message. Triggers on: "close the session", "update versions", "save the bundle", "I'm done…

snapsynapse/skill-provenance · 83 tokens

validate

Run a focused validation check for a skill bundle. Use when the user asks to validate, verify hashes, check MANIFEST.yaml, confirm files are present, or distinguish a canonical bundle from a derived install or registry copy without opening or closing a full editing session.

snapsynapse/skill-provenance · 54 tokens