Skip to content
Agentmart
Submit a tool

security-audit

Focused security audit — runs the security + adversarial reviewers with STRIDE and deployment-context severity, then consolidates.

Skill by mateim4

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/mateim4-security-audit

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

Focused security audit — runs the security + adversarial reviewers with STRIDE and deployment-context severity, then consolidates. Use for a security-only pass.

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-audit

What's inside

Skill name
security-audit
Description
Focused security audit — runs the security + adversarial reviewers with STRIDE and deployment-context severity, then consolidates. Use for a security-only pass.
License
MIT
Instructions
21 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# AgentStrap security audit

A security-focused subset of `/agentstrap:audit`.

## Step 0 — Deployment context

Use the argument if given, else `.agentstrap/config.json` `audit.deployment_context`, else default `internet-facing`. This drives the severity badges (🔴 APPLIES / 🟡 REDUCED / ⚪ N/A) shown in the scale below.

## Step 1 — Dispatch (parallel)

Dispatch `audit-security` and `audit-adversarial` via the Task tool, scoped to the code. **In each task prompt include** the severity scale, the deployment context, and the finding format:

> **P0** exploitable now / data loss · **P1** serious defect, fix now · **P2** real but not urgent · **P3** polish. Tag **STRIDE** (Spoofing/Tampering/Repudiation/Info-disclosure/DoS/Elevation) + badge 🔴 APPLIES / 🟡 REDUCED / ⚪ N/A per deployment context (default `internet-facing` = 🔴).

Both tag findings with STRIDE + a context badge.

## Step 2 — Consolidate and report

Run the `consolidate-findings` steps. Group by STRIDE category and tier. Compare against any previous security audit in the vault and flag regressions / fixes / new findings. Write the report to `30 - Engineering/Audits/Security Audit YYYY-MM-DD.md` (or print). Review only — do not change code unless asked.

From mateim4/agentstrap-v2, MIT.

More from mateim4/agentstrap-v2

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 14, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
Repository
github.com/mateim4/agentstrap-v2
First seen
Oct 24, 2026
Last checked
Oct 24, 2026
Source
GitHubgithub-graphql

More from mateim4

Cite this page

security-audit skill. Agent Mart. https://agentmart.dev/skills/mateim4-security-audit (last updated 2026-10-24)