security-audit

security-audit is a skill for Claude Code, Codex from alexmond/jhelm. It costs 22 tokens per session (515 once invoked), scanned A, original, Apache-2.0.

A code review that searches jhelm for common security flaws, such as unsafe file paths, command execution, parsing, and exposed secrets.

In plain words
What is it for?
Use it to scan the whole jhelm codebase or a selected file or module for OWASP-style security risks.
Why use it?
It helps find places where untrusted input could let someone access files, run commands, or read sensitive data before those weaknesses reach users.

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/alexmond/jhelm/security-audit
Any agent
npx skills add alexmond/jhelm --skill security-audit
Clone the repo
git clone --depth 1 https://github.com/alexmond/jhelm

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-audit

README.md
[![agentmods](https://agentmods.dev/badge/skills/alexmond/jhelm/security-audit.svg)](https://agentmods.dev/skills/alexmond/jhelm/security-audit)
Your own site
<a href="https://agentmods.dev/skills/alexmond/jhelm/security-audit"><img src="https://agentmods.dev/badge/skills/alexmond/jhelm/security-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 515 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 $0.00022 $0.00515
Opus 5 $0.00011 $0.00258
Sonnet 5 $0.00004 $0.00103
Haiku 4.5 $0.00002 $0.00052

Measured 4d ago against content hash 22102095e5fd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

security-audit 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.

.claude/skills/security-audit/SKILL.md · 68 lines

What it actually says

Security Audit for jhelm

Scan the codebase (or specific module/file) for common security vulnerabilities.

Scope

If $ARGUMENTS is provided, limit the scan to that module or path. Otherwise, scan all modules.

Checks to Perform

1. Path Traversal

Search for file path construction from untrusted input:

Grep for: new File(.*,.*getName|new File(.*,.*entry|Path.of(.*input|Paths.get(.*input

Verify each hit has canonical path validation or sanitization.

2. Command Injection

Search for Runtime.exec, ProcessBuilder with user input:

Grep for: Runtime.getRuntime|ProcessBuilder|\.exec\(

Verify arguments are not constructed from user input without sanitization.

3. YAML Deserialization

Search for unsafe YAML parsing:

Grep for: new Yaml\(\)|Yaml.load\(|ObjectMapper.*readValue.*untrusted

Verify SnakeYAML SafeConstructor is used, or Jackson is configured safely.

4. XML External Entity (XXE)

Search for XML parsing without disabling external entities:

Grep for: DocumentBuilder|SAXParser|XMLReader|TransformerFactory
5. Sensitive Data Exposure

Search for credentials, tokens, or keys in code:

Grep for: password|secret|token|apiKey|private.key (case-insensitive, exclude test files)

Verify no hardcoded credentials exist.

6. Input Validation at Boundaries

Check REST endpoints and CLI argument handlers validate input:

  • Chart names, repository URLs, file paths from user
  • OCI registry responses
  • Helm chart metadata (Chart.yaml fields)

Report Format

Severity Location Issue Recommendation
CRITICAL file:line Description Fix suggestion
HIGH file:line Description Fix suggestion
MEDIUM file:line Description Fix suggestion
LOW file:line Description Fix suggestion

Report only confirmed findings, not theoretical risks. If clean, say "No vulnerabilities found."

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 · 68 lines · 22 tokens per session scan A 22102095e5fd

Subscribe to this mod's changes

security-audit is a skill published in the GitHub repository alexmond/jhelm (4 stars, last pushed 10d ago), licensed Apache-2.0. It adds 22 tokens to every session and 515 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 2026-08-31.