Skip to content
Agentmart
Submit a tool

security-guidance

Provide lightweight security guidance while implementing or reviewing application changes, focusing on the changed trust boundaries and common high-impact…

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-security-guidance

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

Provide lightweight security guidance while implementing or reviewing application changes, focusing on the changed trust boundaries and common high-impact weakness classes. This is not a full security audit.

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/security-guidance

What's inside

Skill name
security-guidance
Description
Provide lightweight security guidance while implementing or reviewing application changes, focusing on the changed trust boundaries and common high-impact weakness classes. This is not a full security audit.
License
MIT
Instructions
20 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Security Guidance

Use an installed native security-guidance integration when available. Otherwise
perform a focused review of the requested change.

For changed code, identify:

- untrusted inputs and output contexts;
- authentication, authorization, tenancy, and object ownership decisions;
- database, command, template, path, URL, parser, and deserialization sinks;
- secrets, tokens, personal data, and sensitive logs;
- outbound requests, redirects, uploads, and filesystem access;
- dependency or configuration changes that alter exposure.

Report only actionable issues supported by a plausible path and code evidence.
Include impact, preconditions, confidence, and the smallest remediation. Distinguish
confirmed findings from hardening suggestions. Do not broaden ordinary feature
work into a repository-wide audit unless requested.

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

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