security SKILL.md skillA
security from vanducng/skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add vanducng/skills/security@v0.2.0Pins v0.2.0 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- vanducng/skills
- Path
skills/security/SKILL.md- Versions recorded
- 6
- Latest version
- v0.2.0, committed Sep 20, 2026
- First version recorded
- Jun 14, 2026
- Size
- 7,910 bytes
- Repository stars
- 8
- License
- MIT
Threat-modeled security audit using STRIDE + OWASP (incl. OWASP LLM Top-10), Cloudflare-style evidence bar (confirmed / needs_validation / rejected), optional red-team discovery, adversarial verify, and an autoresearch-style fix loop. Use for defensive security review, vulnerability discovery, threat modeling, prompt-injection / LLM / MCP security, multi-tenant isolation, and authorized remediation. Triggers: 'security audit', 'STRIDE', 'OWASP', 'find vulnerabilities', 'threat model'…
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 > STRIDE + OWASP from multiple attacker perspectives → evidence-gated findings, optionally auto-fixed. ## Scope & posture **Defensive / authorized use only.** Run against code you own or are authorized to audit. This skill performs review and authorized remediation; it does **not** produce weaponized exploits, mass-targeting tooling, or detection-evasion for malicious use. **Credential masking is mandatory** - even when the secret *is* the finding. Mask per the table in `vd:optimize-loop`'s SKILL.md (API keys → `<REDACTED_TOKEN>`, connection strings → `…:<REDACTED_PASSWORD>@…`, env values → reference the name). No report or PoC may contain a live secret or a copy-paste-ready exploit with real credentials - write PoCs as templates the user fills in. Do not probe deployed / shared / production endpoints. Prefer source review and local dummy fixtures. If a decisive fact lives only in deployment config you cannot see, use `needs_validation` - do not guess. ## What this is - and isn't …
Read the whole file at its exact version.
How to install
mdr add vanducng/skills/security@sha256:a95b410baf4d6792The line at the top of this page pins the label v0.2.0, 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_5jik3bhh64nffwzy)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 6 versions of this file, between Jun 14, 2026 and Sep 20, 2026, about one every 20 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| v0.2.0 latest | 2026-09-20 | c1f8315 | 7,910 B | A | view · diff |
| v0.1.0 | 2026-09-11 | 9e58ef3 | 4,688 B | A | view · diff |
| v0.1.0 | 2026-07-24 | 51405ee | 4,688 B | A | view · diff |
| v0.1.0 | 2026-06-17 | 55fdabe | 4,716 B | A | view · diff |
| v0.1.0 | 2026-06-14 | f784a33 | 4,830 B | A | view · diff |
| v0.1.0 | 2026-06-14 | 560f72b | 4,825 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 (7910 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
vanducng/skills · 8 stars · license MIT · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_5jik3bhh64nffwzy GET https://markdownregistry.com/api/v1/resolve?ref=vanducng/skills/security GET https://markdownregistry.com/api/v1/blob/a95b410baf4d67926679c80937b1a60c3ef6fd1a0b64e48992f48b52840a28b2
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.