security-audit

security-audit is a command for Cursor from emaraschio/cursor-commands. It costs 11 tokens per session (444 once invoked), scanned A, original, MIT.

A security review of a codebase or a proposed code change. A codebase is the collection of source files that make up a software project.

In plain words
What is it for?
Use it to review an entire project or a specific change for security issues. It also helps assess whether a known dependency vulnerability can actually be reached and ensures discovered credentials are reported without revealing their values.
Why use it?
Security problems can be missed when code changes are reviewed only for whether they work. The audit provides a structured process for examining risks, including known flaws in dependencies and exposed secrets.

Command for Cursor

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 commands/emaraschio/cursor-commands/security-audit
Clone the repo
git clone --depth 1 https://github.com/emaraschio/cursor-commands

Made for: Cursor.

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/commands/emaraschio/cursor-commands/security-audit.svg)](https://agentmods.dev/commands/emaraschio/cursor-commands/security-audit)
Your own site
<a href="https://agentmods.dev/commands/emaraschio/cursor-commands/security-audit"><img src="https://agentmods.dev/badge/commands/emaraschio/cursor-commands/security-audit.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 444 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 $0.00011 $0.00444
Opus 5 $0.00005 $0.00222
Sonnet 5 $0.00002 $0.00089
Haiku 4.5 $0.00001 $0.00044

Measured 4d ago against content hash 86f54551da0a, 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.

.cursor/commands/security-audit.md · 39 lines

What it actually says

Overview

Security audit of codebase or change. Full workflow: .cursor/skill-contracts/security-audit/SKILL.md (user install: ~/.cursor/skill-contracts/security-audit/SKILL.md).

Defaults

None. See skill for workflow defaults.

Steps

  1. Read .cursor/skill-contracts/security-audit/SKILL.md for the full agent contract; if that file is missing, read ~/.cursor/skill-contracts/security-audit/SKILL.md.
  2. Execute the workflow in order; do not skip safety steps.
  3. Report outcomes per skill (summary, tables, or checklist as specified).

Anti-patterns

  • Triage dependency CVEs, never ignore them. Trigger: the dependency audit surfaces a known CVE. Wrong: noting the version and moving on. Correct: assess severity and whether the path is reachable, then flag or patch the affected dependency. Reason: an unhandled known CVE is exactly the exploit route an audit exists to close.
  • Keep live secrets out of findings. Trigger: the scan turns up a real credential, token, or key. Wrong: pasting the live value into the report to evidence the finding. Correct: redact the value and cite only its location. Reason: an audit report circulates widely, so a pasted secret leaks it further.
  • Do not run write or destructive operations without explicit consent. Reason: an audit is read-first, so commits, merges, pushes, or production scripts run without an explicit request are hard to undo.

Examples

  • /security-audit

Maintainers

Behavioral eval: .cursor/skill-contracts/security-audit/eval/cases.md. Ship gate sections: A, S before changing SKILL.md or this command.

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 · 39 lines · 11 tokens per session scan A 86f54551da0a

Subscribe to this mod's changes

security-audit is a command published in the GitHub repository emaraschio/cursor-commands (9 stars, last pushed 27d ago), licensed MIT. It adds 11 tokens to every session and 444 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.