Skip to content
Agentmart
Submit a tool

claude-security

Conduct an authorized, deep application security review using the native Claude Security capability when available, with a portable evidence-driven fallback…

Skill by NeroWasTrolled

IndexedMIT
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/nerowastrolled-claude-security

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Conduct an authorized, deep application security review using the native Claude Security capability when available, with a portable evidence-driven fallback when it is not. Use only when a broad security audit is explicitly requested.

Use cases: security

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/claude-security

What's inside

Skill name
claude-security
Description
Conduct an authorized, deep application security review using the native Claude Security capability when available, with a portable evidence-driven fallback when it is not. Use only when a broad security audit is explicitly requested.
License
MIT
Instructions
21 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Claude Security Adapter

If the official Claude Security plugin is available, invoke its maintained audit
workflow and follow its permissions and output contract. Do not claim plugin use
when it is unavailable.

Fallback workflow:

1. Confirm scope, authorization, environment, excluded systems, and output sensitivity.
2. Build an architecture and trust-boundary model from the code and configuration.
3. Rank attack surfaces by reachable privilege and asset impact.
4. Review high-risk flows across authentication, authorization, injection,
   deserialization, SSRF, file handling, secrets, cryptography, and business logic.
5. Verify each candidate through code tracing, focused analysis, or safe reproduction.
6. Deduplicate findings by root cause and document evidence and preconditions.
7. Produce fixes only when requested, keeping remediation minimal and testable.

Never attack third-party or production systems without explicit authorization.
Absence of findings is not proof of security.

From NeroWasTrolled/gabriel-ai-devkit, MIT.

More from NeroWasTrolled/gabriel-ai-devkit

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Sep 3, 2026 (1 month ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/NeroWasTrolled/gabriel-ai-devkit
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from NeroWasTrolled

Cite this page

claude-security skill. Agent Mart. https://agentmart.dev/skills/nerowastrolled-claude-security (last updated 2026-10-24)