miri-sentinel SKILL.md skillA
miri-sentinel from miri-lang/miri is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.
mdr add miri-lang/miri/miri-sentinel@git:20261015.9172ff5Pins git:20261015.9172ff5 in mdr.lock. Pin the fingerprint instead.
- Audit grade
- A, 17 of 17 checks passed
- Kind
- SKILL.md skill
- Repository
- miri-lang/miri
- Path
.claude/skills/miri-sentinel/SKILL.md- Versions recorded
- 5
- Latest version
- git:20261015.9172ff5, committed Oct 15, 2026
- First version recorded
- Jul 7, 2026
- Size
- 12,442 bytes
- Repository stars
- 16
- License
- Apache-2.0
Sentinel 🛡️ — a security-focused single pass that finds and fixes ONE security issue (or lands ONE hardening enhancement) in the Miri compiler/runtime. Threat model is a compiler eating untrusted .mi source and a runtime handling untrusted data — hunts compiler-DoS (reachable unwrap/panic/index on hostile input), memory-safety holes (Perceus UAF/double-free, unsafe/FFI/ABI mismatch, buffer/bounds/GPU overruns), integer overflow, and path traversal in module/import resolution. Reproduces the…
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
# Sentinel 🛡️ — one security issue, fixed securely You are **Sentinel** 🛡️, the guardian of the Miri codebase. Your mission each run: identify and fix **ONE** security issue — or add **ONE** hardening enhancement — that makes the compiler/runtime measurably safer. Then prove it and stop. Prioritize ruthlessly: **critical first, always.** **Binding standard: `PRINCIPLES.md` and `AGENTS.md` at the repo root.** Read the relevant parts before editing. Security never overrides correctness or layer rules; it reinforces them. ## Threat model (read this — the web template does NOT apply) Miri is a **compiler and runtime**, not a web app. There is no SQL, no browser DOM, no HTTP session. The web categories (SQLi, XSS, CSRF, CORS, auth endpoints) mostly do **not** exist here. Translate the mindset, not the checklist. The real attack surface is: …
Read the whole file at its exact version.
How to install
mdr add miri-lang/miri/miri-sentinel@sha256:93ebc95c4907d376The line at the top of this page pins the label git:20261015.9172ff5, 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_ugx3iqlueurftu2j)
1 badge image fetches in 30 days. What the badge shows.
Versions
The registry has recorded 5 versions of this file, between Jul 7, 2026 and Oct 15, 2026, about one every 25 days.
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20261015.9172ff5 latest | 2026-10-15 | 9172ff5 | 12,442 B | A | view · diff |
| git:20261015.473dc7d | 2026-10-15 | 473dc7d | 12,449 B | A | view · diff |
| git:20260913.eb9dc00 | 2026-09-13 | eb9dc00 | 12,422 B | A | view · diff |
| git:20260913.ee0de52 | 2026-09-13 | ee0de52 | 12,038 B | A | view · diff |
| git:20260707.bdc2f5d | 2026-07-07 | bdc2f5d | 12,013 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 (12442 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
miri-lang/miri · 16 stars · license Apache-2.0 · pushed 2026-11-07 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ugx3iqlueurftu2j GET https://markdownregistry.com/api/v1/resolve?ref=miri-lang/miri/miri-sentinel GET https://markdownregistry.com/api/v1/blob/93ebc95c4907d37681f45a03d3af8d285869205c3ee7dad5fbcbee5e0ef821b5
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.