sota-skill-security SKILL.md skillA
sota-skill-security from martinholovsky/sota-skills is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add martinholovsky/sota-skills/sota-skill-security@git:20261024.8dd2b0aPins git:20261024.8dd2b0a in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- martinholovsky/sota-skills
- Path
skills/sota-skill-security/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261024.8dd2b0a, committed Oct 24, 2026
- First version recorded
- Sep 6, 2026
- Size
- 9,206 bytes
- Repository stars
- 26
- License
- CC-BY-4.0
Security for AI agent skills, plugins and instruction bundles (2026) — the supply chain of things that tell an agent what to do. Use when installing, authoring, reviewing, updating or auditing any skill, plugin, ruleset or agent file an agent loads as instructions, including your own; when a repository you do not fully trust contains agent-readable instruction files; and when deciding what an installed skill may reach. Covers provenance and pinning, review-before-install, the instruction trust…
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
# SOTA Skill & Instruction-Bundle Security (2026) ## Purpose A skill is **executable influence**. It does not run in the interpreter, it runs in the model — and the model then runs the tools. Everything the software supply chain learned about dependencies applies to instruction bundles, with one difference that makes it worse: **a malicious dependency's code has to run — at install, import or call — and a malicious skill only has to be loaded**; some skills also run shell commands the moment they are invoked ([`rules/02`](rules/02-trust-boundary-and-capability.md) §1). This skill exists because the ecosystem now has all the ingredients of a supply chain — marketplaces, plugins, `git clone` installs, auto-loading descriptions, transitive resources — and almost none of the controls. A library that tells everyone else to pin, verify provenance, and minimise capability, while installing its own instructions by curl, has not noticed it is a supply chain. **The trust boundary is the point.** Anyone who can modify a file your agent loads as instructions can change what your agent does, in every session, silently. That …
Read the whole file at its exact version.
How to install
mdr add martinholovsky/sota-skills/sota-skill-security@sha256:e5d95de6ddc46e3aThe line at the top of this page pins the label git:20261024.8dd2b0a, 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_lr5botu2hdl2tsrl)
4 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Sep 6, 2026 and Oct 24, 2026, about one every 12 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261024.8dd2b0a latest | 2026-10-24 | 8dd2b0a | 9,206 B | A | view · diff |
| git:20261012.ae1b29b | 2026-10-12 | ae1b29b | 8,965 B | A | view · diff |
| git:20260926.5e96645 | 2026-09-26 | 5e96645 | 7,858 B | A | view · diff |
| git:20260911.9cd2dc7 | 2026-09-11 | 9cd2dc7 | 7,742 B | A | view · diff |
| git:20260906.b3ca4bb | 2026-09-06 | b3ca4bb | 7,506 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 (9206 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
martinholovsky/sota-skills · 26 stars · license CC-BY-4.0 · pushed 2026-11-05 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_lr5botu2hdl2tsrl GET https://markdownregistry.com/api/v1/resolve?ref=martinholovsky/sota-skills/sota-skill-security GET https://markdownregistry.com/api/v1/blob/e5d95de6ddc46e3a0240842a0448315cf3553f356cbf66ee4f02e5f26cb49e8a
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.