audit-report

audit-report is a command for coding agents from sembraniteam/claude-plugins. It costs 44 tokens per session (715 once invoked), scanned A, original, MIT.

A command that creates a complete security-audit report from findings already discussed during the current coding session. It can also create SARIF, a standard format used by GitHub code scanning.

In plain words
What is it for?
It collects vulnerability and dependency findings, their severity and locations, the audit mode, and project details, then writes SECURITY-AUDIT.md and optionally SECURITY-AUDIT.sarif.json.
Why use it?
It turns scattered audit findings into a standalone report that can be saved, shared, and reviewed later.

Command

Part of the security-auditor plugin — 1 skill, 7 commands, 3 agents shipped together

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/sembraniteam/claude-plugins/audit-report
Clone the repo
git clone --depth 1 https://github.com/sembraniteam/claude-plugins

Or install security-auditor, the plugin that ships this one along with the rest of its 1 skill, 7 commands, 3 agents.

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 audit-report

README.md
[![agentmods](https://agentmods.dev/badge/commands/sembraniteam/claude-plugins/audit-report.svg)](https://agentmods.dev/commands/sembraniteam/claude-plugins/audit-report)
Your own site
<a href="https://agentmods.dev/commands/sembraniteam/claude-plugins/audit-report"><img src="https://agentmods.dev/badge/commands/sembraniteam/claude-plugins/audit-report.svg" alt="Measured on agentmods" height="20"></a>
Per session 44 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 715 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 $0.00044 $0.00715
Opus 5 $0.00022 $0.00358
Sonnet 5 $0.00009 $0.00143
Haiku 4.5 $0.00004 $0.00072

Measured 4d ago against content hash 1ef402493785, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

audit-report 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.

security-auditor/commands/audit-report.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are regenerating the security audit report from this session using the security-auditor plugin.

What this command does

It collects all findings discussed in this conversation (from /audit, /audit-diff, /audit-file, or /audit-deps runs) and formats them into a complete, standalone SECURITY-AUDIT.md using the report template from the secure-code-review skill. If $ARGUMENTS contains --sarif, it also writes SECURITY-AUDIT.sarif.json.

Step 1 — Collect session findings

Look back through this conversation and gather:

  • All code vulnerability findings (with CWE IDs, file:line locations, evidence snippets, severity)
  • All dependency CVE findings (package, version, CVE ID, CVSS, fixed version)
  • The audit mode used (development/production)
  • The project name and stack

If no audit has been run in this session yet, respond:

"No audit findings found in this session. Run /audit first to generate findings, then use /audit-report to save them."

Step 2 — Format the report

Apply the full report template from the secure-code-review skill:

  1. Executive Summary — project name, date, stack, total findings by severity, top-3 critical issues in plain language
  2. Findings Summary Table — all findings ordered by severity
  3. Finding Details — one section per finding with CWE, evidence, impact, remediation
  4. Dependency Vulnerabilities — the CVE table (if deps were scanned)
  5. Priority Recommendations — top 5 actions ordered by risk × effort

Include in the header:

Audit Date: <today's date>
Audit Mode: development | production
Generated by: security-auditor plugin v<version — read from `.claude-plugin/plugin.json`, never hardcode>
Disclaimer: This report is a defensive audit aid. Findings may include false positives or miss vulnerabilities not detectable via static analysis. Human review and professional penetration testing are recommended for production systems.

Step 3 — Save the file

Write the complete report to SECURITY-AUDIT.md in the current working directory.

Read the full file on GitHub · 53 lines

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 · 53 lines · 44 tokens per session scan A 1ef402493785

Subscribe to this mod's changes

audit-report is a command published in the GitHub repository sembraniteam/claude-plugins (2 stars, last pushed 1mo ago), licensed MIT. It adds 44 tokens to every session and 715 once invoked, about $0.0002 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.