security-audit SKILL.md skillA
security-audit from borghei/claude-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add borghei/claude-skills/security-audit@v1.0.0Pins v1.0.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- borghei/claude-skills
- Path
engineering/security-audit/SKILL.md- Versions recorded
- 1
- Latest version
- v1.0.0, committed Oct 7, 2026
- Size
- 16,558 bytes
- Repository stars
- 954
- License
- a license file GitHub does not identify
Multi-agent source security audit with a coverage ledger, independently verified findings, and machine-checked records. Use when asked to audit a codebase, find vulnerabilities, or run a source-level pen test.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
# Security Audit A single pass over a codebase finds the bugs that pass happened to look at and reports them with whatever confidence the reader had that day. This skill replaces that with a process: a lead agent maps the target, writes down exactly what will be examined, sends isolated hunters at each piece, has a different agent try to disprove every claim, and only then writes a report — from records that two validators have checked. The output is a set of findings in three honest states: **confirmed** (traced through source and reproduced locally), **needs validation** (a specific hypothesis blocked on one named fact), and **rejected** (disproved, kept so it is not raised again). **Scope boundary.** This is a defensive, source-first audit of a repository. It does **not** send traffic to deployed systems — that needs an engagement plan from `red-team`. It does **not** produce a STRIDE threat model or scan for secrets as its main job — that is `senior-security`. It does **not** query live cloud accounts — that is `cloud-security`. It does **not** list dependency CVEs — that is `dependency-auditor`. What lives here is finding, verifying, and …
Read the whole file at its exact version.
How to install
mdr add borghei/claude-skills/security-audit@sha256:2e53a06b2b9854a2The line at the top of this page pins the label v1.0.0, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
[](https://markdownregistry.com/a/art_dk2i2vl3wg7miuxm)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 1 version of this file, committed on Oct 7, 2026.
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (16558 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
borghei/claude-skills · 954 stars · license a license file GitHub does not identify · pushed 2026-10-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_dk2i2vl3wg7miuxm GET https://markdownregistry.com/api/v1/resolve?ref=borghei/claude-skills/security-audit GET https://markdownregistry.com/api/v1/blob/2e53a06b2b9854a28e923f3fb7449f3e613eccabad26bc50cd4d6ea0b2d2bd9f
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.
More from borghei/claude-skills
Every file in borghei/claude-skills