New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Security Audit

by ziggy42 in ziggy42/epsilon

A skill your agent uses to perform a security-focused audit of the codebase to identify vulnerabilities, sandbox escapes, and logic flaws.

Apache-2.0Auto-check passedSecurity

Install Security Audit

skills CLI
$ npx skills add ziggy42/epsilon --skill security-audit -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ziggy42/epsilon security-audit --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ziggy42/epsilon.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/security-audit .claude/skills/security-audit && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
security-audit
GitHub stars
439
Token cost
~924 tokens
SKILL.md length
397 words
Files
1
Skills in repo
3
Repo updated
First seen
Licence
Apache-2.0

At a glance

A skill your agent uses to perform a security-focused audit of the codebase to identify vulnerabilities, sandbox escapes, and logic flaws.

  • Works in 3 steps: Investigation Methodology → Verification & PoC Generation → Reporting Format
  • Perform a security-focused audit of the codebase to identify vulnerabilities
  • SKILL.md covers Overview, Procedure and Critical Rules
  • Calls go

What it does

Security Audit is an agent skill from ziggy42/epsilon. Use this skill to perform a security-focused audit of the codebase to identify vulnerabilities, sandbox escapes, and logic flaws.

Its SKILL.md is about 920 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Security, covering Security review. It works with WebAssembly and Go. The repository describes itself as: A WASM virtual machine written in Go with 0 dependencies. The licence is Apache-2.0.

When your agent uses it

  • Perform a security-focused audit of the codebase to identify vulnerabilities
  • Sandbox escapes

Example prompts

  • “/security-audit”

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Investigation Methodology
  2. Verification & PoC Generation
  3. Reporting Format

What it can do on your machine

Read from SKILL.md and the folder at commit 64a2225. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • go

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Security Audit loads about 924 tokens when it runs. Until then it costs about 36 tokens; SKILL.md has 397 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~36
When it runs · the whole SKILL.md, loaded when a task matches
~924

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ziggy42/epsilon at commit 64a2225, republished under its Apache-2.0 licence (© ziggy42). 397 words, ~924 tokens.

Download SKILL.mdSave it as .claude/skills/security-audit/SKILL.md (or your agent's skills folder).
name
security-audit
description
Use this skill to perform a security-focused audit of the codebase to identify vulnerabilities, sandbox escapes, and logic flaws.

Security Audit

Overview

Perform a rigorous security assessment of the Epsilon WebAssembly engine. The objective is to identify exploitable vulnerabilities, verify sandbox isolation, and ensure safe host interactions. Do not focus just on local changes, look at the project as a whole.

Procedure

1. Investigation Methodology

Your goal is to find flaws that automated tools or basic reviews miss. Do not restrict yourself to a predefined checklist. Instead, employ a systematic, deep-dive methodology:

  1. Select Entry Points: Begin at the boundaries where untrusted input enters the system or interacts with the host. High-value starting points include the main execution loop (e.g., epsilon/vm.go), host interface boundaries (e.g., wasip1/), or memory indexing operations.
  2. Spawn Specialized Subagents: For complex files or distinct components, spawn focused subagents to audit them in isolation. Instruct these subagents to investigate specific mechanics deeply rather than doing a shallow read.
  3. Trace Execution Paths: Follow the flow of untrusted data (instructions, indices, offsets, file descriptors) from ingestion to execution. Assume the input is malicious.
  4. Audit Specification Deviations: Compare the implementation of complex instructions against the WebAssembly 2.0 formal execution rules. Any optimization that skips or defers a spec-mandated check is a potential vulnerability.
Show full SKILL.md (200 more words)Show less
2. Verification & PoC Generation

Never report a bug without actively triggering it locally.

  1. Create a Vulnerability Directory: For each confirmed flaw, create a new directory at vulnerabilities/[id]/ (e.g., vulnerabilities/VULN-01/).
  2. Write the PoC: Place a Go test or a minimal .wasm file that reliably triggers the flaw inside the specific vulnerability directory.
  3. Test Constraints:
    • Do NOT write tests that invoke a single VM instance concurrently.
    • To prove state leakage, write tests that run multiple independent VMs concurrently using go test -race.
    • To prove parser crashes or bounds-check failures, write a standard Go fuzz test (go test -fuzz).
3. Reporting Format

If a vulnerability is confirmed locally, document it in a README.md file located within the corresponding vulnerabilities/[id]/ directory using this exact format:

markdown
# [Concise Title of the Issue]

**Severity:** [Critical | High | Medium | Low] **Affected Component:** [File
path and function name] **Bug Type:** [e.g., Path Traversal, OOB Slice Panic,
State Leakage]

## Root Cause

[Strictly technical explanation of the code flaw. Cite specific lines. Explain
the gap between intended logic and actual behavior.]

## Execution Flow

[Step-by-step breakdown of how the PoC triggers the bug.]

## Observable Impact

[Exact result: e.g., "Go panic: index out of range", "Race condition detected".]

## Proposed Remediation

[Provide the specific Go code diff to patch the vulnerability.]

Critical Rules

  1. Isolation: You are strictly prohibited from modifying any existing files in the repository. All work, including PoCs and documentation, must be contained within the vulnerabilities/ directory.
  2. No Panics: The engine must never panic on untrusted WASM or invalid WASI arguments. All bounds and inputs must be validated and returned as standard Go errors.
  3. No Speculation: If you cannot write a failing Go test to prove the bug, do not report it.

© ziggy42, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/security-audit of ziggy42/epsilon.

Open the folder on GitHubat commit 64a2225

Compare with similar skills

Security Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Security Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Security Audit this skillziggy42/epsilon439—~924Automated safety check: PassApache-2.0
Ghost Scan Depsghostsecurity/skills408—~1.3kAutomated safety check: NotesApache-2.0
Cosmos Vulnerability Scannertrailofbits/skills7.4k—~2.7kAutomated safety check: PassCC-BY-SA-4.0
Time Aware Dependency Cve ScannerArabelaTso/Skills-4-SE253—~2.1kAutomated safety check: PassApache-2.0
Security UpdatesSmilyOrg/photofield608—~808Automated safety check: PassMIT
Security Auditoreigent-ai/eigent15k—~1.8kAutomated safety check: NotesApache-2.0

Similar skills

  • Ghost Scan Deps

    ghostsecurity/skills

    Ghost Security - Software Composition Analysis (SCA) scanner.

    408 GitHub stars~1.3k tokensUpdated 10 days ago
    SecurityAuto-check: notes

  • Cosmos Vulnerability Scanner

    trailofbits/skills

    Official

    Scans Cosmos SDK modules and CosmWasm contracts for consensus-critical flaws that can halt a chain, lose funds or diverge state, using parallel scanning agents.

    7.4k GitHub stars~2.7k tokensUpdated yesterday
    SecurityAuto-check passed

  • Time Aware Dependency Cve Scanner

    ArabelaTso/Skills-4-SE

    Scan repositories for newly disclosed CVEs in dependencies after a specific cutoff date.

    253 GitHub stars~2.1k tokensUpdated 1 mo ago
    SecurityAuto-check passed

  • Security Updates

    SmilyOrg/photofield

    Check and apply security updates across the photofield project (api/Go, ui/npm, docs/npm, e2e/npm).

    608 GitHub stars~808 tokensUpdated 1 mo ago
    Testing & QAAuto-check passed

  • Security Auditor

    eigent-ai/eigent

    Audits source code, dependencies and config files for vulnerabilities and hardcoded secrets, using two bundled Python scanners and an OWASP Top 10 checklist.

    15k GitHub stars~1.8k tokensUpdated today
    SecurityAuto-check: notes

  • Security Review

    jewbetcha/opentrace

    A skill your agent uses when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment/sensitive features.

    116 GitHub starsUsed in 18 repos~3.1k tokens
    SecurityAuto-check: notes

More from ziggy42/epsilon

  • Code Review

    ziggy42/epsilon

    A skill your agent uses when the user asks for a code review.

    439 GitHub stars~1.7k tokensUpdated 4 days ago
    Auto-check passed

  • Release

    ziggy42/epsilon

    A skill your agent uses when the user wants to cut a new release.

    439 GitHub stars~1.1k tokensUpdated 4 days ago
    Auto-check passed

Works with

Categories

Questions about Security Audit

What does Security Audit do?

A skill your agent uses to perform a security-focused audit of the codebase to identify vulnerabilities, sandbox escapes, and logic flaws. Security Audit is an agent skill from ziggy42/epsilon. Use this skill to perform a security-focused audit of the codebase to identify vulnerabilities, sandbox escapes, and logic flaws.

When should I use Security Audit?

Security Audit fits situations like: perform a security-focused audit of the codebase to identify vulnerabilities; sandbox escapes.

How do I install Security Audit in Claude Code?

Run `npx skills add ziggy42/epsilon --skill security-audit -a claude-code`. Or copy the skill folder (.agents/skills/security-audit in ziggy42/epsilon) into .claude/skills/security-audit in your project. Claude Code loads it when a task matches its description.

How do I install Security Audit in Codex?

Run `npx skills add ziggy42/epsilon --skill security-audit -a codex`. Or copy the skill folder (.agents/skills/security-audit in ziggy42/epsilon) into .agents/skills/security-audit in your project. Codex loads it when a task matches its description.

Can I use Security Audit in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ziggy42/epsilon --skill security-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/security-audit, .gemini/skills/security-audit, .github/skills/security-audit and .opencode/skills/security-audit in your project.

What does Security Audit need to run?

Going by SKILL.md and its folder, Security Audit needs the command-line tools its instructions call (go).

Does Security Audit access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Security Audit safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Security Audit use?

Security Audit is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Security Audit use?

About 924 tokens (SKILL.md is roughly 3.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Security Audit?

Skills that share tags, products or a category with Security Audit: Ghost Scan Deps (ghostsecurity/skills, 408 stars), Cosmos Vulnerability Scanner (trailofbits/skills, 7.4k stars), Time Aware Dependency Cve Scanner (ArabelaTso/Skills-4-SE, 253 stars) and Security Updates (SmilyOrg/photofield, 608 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Security Audit?

ziggy42 (a GitHub user) maintains it in ziggy42/epsilon, which has 439 GitHub stars. The repository holds 3 skills in this directory. The repository was last updated on October 4, 2026.

Source: ziggy42/epsilon on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.