security-scan

security-scan is a skill for Claude Code, Codex from New1Direction/korgex. It costs 34 tokens per session (475 once invoked), scanned A, original, MIT.

A read-only security-checking workflow for code and dependencies. It looks for known vulnerabilities, exposed secrets, unsafe settings, and certain insecure code patterns.

In plain words
What is it for?
Use it after adding dependencies or changing authentication, secrets, file access, subprocesses, or network code, and to gate a CI pipeline on serious findings.
Why use it?
Security problems can remain hidden in new code or packages until they are exploited. A recorded scan provides specific findings that can be checked before work is declared complete.

Skill for Claude CodeCodex

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 skills/new1direction/korgex/security-scan
Any agent
npx skills add New1Direction/korgex --skill security-scan
Clone the repo
git clone --depth 1 https://github.com/New1Direction/korgex

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-scan

README.md
[![agentmods](https://agentmods.dev/badge/skills/new1direction/korgex/security-scan.svg)](https://agentmods.dev/skills/new1direction/korgex/security-scan)
Your own site
<a href="https://agentmods.dev/skills/new1direction/korgex/security-scan"><img src="https://agentmods.dev/badge/skills/new1direction/korgex/security-scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 475 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 $0.00034 $0.00475
Opus 5 $0.00017 $0.00237
Sonnet 5 $0.00007 $0.00095
Haiku 4.5 $0.00003 $0.00047

Measured 4d ago against content hash fde1fedd7cf7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-scan 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.

src/skills_builtin/security-scan/SKILL.md · 45 lines

What it actually says

Verifiable security scan

When you've added or changed dependencies, written code that touches auth, secrets, subprocess calls, file I/O, or the network — or the user asks "is this secure?" — run a security scan before you finish.

How

Use the security_scan tool. It wraps the best scanner on the machine and is read-only (never modifies files):

  • trivy if installed — vulnerabilities, leaked secrets, IaC misconfig, licenses.
  • otherwise pip-audit (Python dependency CVEs) or bandit (insecure Python patterns).

Calls:

  • security_scan with no args scans the project root.
  • pass path to scan a subtree, or scanner to force trivy / pip-audit / bandit.

For the user (or in CI) the same scan is korgex scan [path] — it exits nonzero when a high/critical finding is present, so it gates a pipeline.

What you get

Each finding has kind (vuln | secret | misconfig | license), severity (critical → low), id (CVE / rule), target (file or pkg@version), and a fix when the scanner knows one. The scan is recorded to the verifiable ledger, so findings are tamper-evident and traceable: korgex why <CVE-or-file> walks a finding back to the prompt that introduced it, and korgex verify proves the report wasn't edited.

Acting on findings

  • Critical / high: fix before finishing — bump the dependency to its fix version, remove and rotate the leaked secret, correct the misconfig — then re-scan to confirm it's gone.
  • False positive: say so explicitly and explain why; don't silently drop it.
  • A surfaced secret is compromised. Never commit it; tell the user to rotate it.
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 · 45 lines · 34 tokens per session scan A fde1fedd7cf7

Subscribe to this mod's changes

security-scan is a skill published in the GitHub repository New1Direction/korgex (5 stars, last pushed 2mo ago), licensed MIT. It adds 34 tokens to every session and 475 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.