security-audit SKILL.md skillA
security-audit from yangkuoshih/security-audit is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add yangkuoshih/security-audit/security-audit@v0.3.0Pins v0.3.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- yangkuoshih/security-audit
- Path
skills/security-audit/SKILL.md- Versions recorded
- 5
- Latest version
- v0.3.0, committed Sep 24, 2026
- First version recorded
- Mar 13, 2026
- Size
- 8,999 bytes
- Repository stars
- 5
- License
- Apache-2.0
Run a lightweight, local security scan of source repositories for hardcoded secrets, risky tracked files, and common vulnerability patterns, then triage redacted findings and produce Markdown, JSON, or SARIF. Use for secret scans, incremental security checks, repository security audits, or GitHub Code Scanning output. Do not use as a dependency-CVE scanner, a substitute for a full SAST/DAST assessment, or for ordinary non-security code review.
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 Run deterministic local scanning and context triage first, then use agent reasoning to validate the remaining vulnerability candidates and prioritize remediation. Describe the result as a lightweight pattern-based audit, not proof that a repository is secure. The preferred scanner requires Python 3.10+. Bash and grep provide a reduced fallback. ## Resolve the skill Let `SKILL_DIR` be the directory containing this `SKILL.md`. Resolve every bundled resource relative to it: - scanner: `SKILL_DIR/scripts/scan-secrets.py` - fallback scanner: `SKILL_DIR/scripts/scan-secrets.sh` - patterns: `SKILL_DIR/scripts/patterns.dat` - report generator: `SKILL_DIR/scripts/generate-report.py` Do not assume a product-specific environment variable or installation layout. ## Safety invariants - Keep scanning and reports local. Never transmit findings, source, or suspected secrets to web services, remote tools, connectors, or telemetry. - Never print or quote raw matches. Scanner output is redacted; preserve that redaction in commentary, reports, logs, and errors. - Do not open files flagged for secret or dangerous-file findings. Triage those …
Read the whole file at its exact version.
How to install
mdr add yangkuoshih/security-audit/security-audit@sha256:6b5f3c3c4eb69480The line at the top of this page pins the label v0.3.0, 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_lptc2fp27e5z3s6d)
2 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Mar 13, 2026 and Sep 24, 2026, about one every 49 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.3.0 latest | 2026-09-24 | 8d4bbd4 | 8,999 B | A | view · diff |
| v0.2.0 | 2026-09-24 | c6b15fa | 8,239 B | A | view · diff |
| v0.1.0 | 2026-03-13 | b6e0895 | 16,388 B | A | view · diff |
| v0.1.0 | 2026-03-13 | 97015f1 | 14,391 B | A | view · diff |
| v0.1.0 | 2026-03-13 | c83b9a4 | 14,296 B | A | view |
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 (8999 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
yangkuoshih/security-audit · 5 stars · license Apache-2.0 · pushed 2026-10-26 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lptc2fp27e5z3s6d GET https://markdownregistry.com/api/v1/resolve?ref=yangkuoshih/security-audit/security-audit GET https://markdownregistry.com/api/v1/blob/6b5f3c3c4eb694805a16365018a5ea2bcc5d61e90e5d8d0ff77d64d10f3b3bd8
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.