aisafety-paper-scout SKILL.md skillA

aisafety-paper-scout from wuyoscar/aisafetyhot-hub is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add wuyoscar/aisafetyhot-hub/aisafety-paper-scout@git:20261013.0db86ec

Pins git:20261013.0db86ec in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
wuyoscar/aisafetyhot-hub
Path
skills/aisafety-paper-scout/SKILL.md
Versions recorded
1
Latest version
git:20261013.0db86ec, committed Oct 13, 2026
Size
2,041 bytes
Repository stars
1,658
License
a license file GitHub does not identify

Find AI safety papers on a direction (jailbreaks, prompt injection, agent security, backdoors, reward hacking, interpretability, evals, AI control, privacy...) from the AI Safety HOT paper library, with one-line takeaways and BibTeX. Use when the user asks for papers, a reading list, or recent work on an AI safety topic.

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

# AI Safety paper scout

Data, no key needed:
- Paper index by direction: `https://raw.githubusercontent.com/wuyoscar/AISafetyHot-Hub/main/daily-papers/topics/<slug>.json` — every paper pushed so far under that direction: `title`, `titleZh`, `line` (what the paper does, one line), `topics`, `venue` (arXiv id or conference), `date`, `url`, `site`, `authors`.
- Daily lists: `https://raw.githubusercontent.com/wuyoscar/AISafetyHot-Hub/main/daily-papers/<year>/<YYYY-MM-DD>.json`.
- Direction slugs and definitions: MCP `aisafetyhot_get_topics`.
- This week's newest picks: MCP `aisafetyhot_get_latest` (`window: "7d"`) → `paperPicks`.

Steps:
1. Map the user's request to 1–3 slugs with `aisafetyhot_get_topics` (e.g. "prompt injection" → `prompt-injection`, "jailbreak" → `jailbreak`).
2. Fetch each slug's JSON; merge, drop duplicates by `id`; add `paperPicks` that match.
3. Rank: what the user asked for first, then newer first; keep up to 15 unless asked for more.
4. Output a table: title (linked), one line on what it does (from `line`), venue, date. Offer the AI Safety HOT reading link (`site`) when present.
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add wuyoscar/aisafetyhot-hub/aisafety-paper-scout@sha256:9b3329bff46226b8

The line at the top of this page pins the label git:20261013.0db86ec, 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.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_p5xaprki5yg3ydlu.svg)](https://markdownregistry.com/a/art_p5xaprki5yg3ydlu)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 1 version of this file, committed on Oct 13, 2026.

versioncommittedcommitsizeaudit
git:20261013.0db86ec latest2026-10-13 0db86ec 2,041 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2041 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

GitHub

wuyoscar/aisafetyhot-hub · 1,658 stars · license a license file GitHub does not identify · pushed 2026-10-22 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_p5xaprki5yg3ydlu
GET https://markdownregistry.com/api/v1/resolve?ref=wuyoscar/aisafetyhot-hub/aisafety-paper-scout
GET https://markdownregistry.com/api/v1/blob/9b3329bff46226b8d4f104558b27645fd22fb4adfb5516a602e1163e3425a0a8

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 wuyoscar/aisafetyhot-hub

AGENTS.md AGENTS.md file
wuyoscar/aisafetyhot-hub · AGENTS.md
git:20261013.0db86ec · audit A · 1,658 stars
aisafety-brief SKILL.md skill
wuyoscar/aisafetyhot-hub · skills/aisafety-brief/SKILL.md · Brief the user on what happened in AI safety in the last 24 hours or 7 days (jailbreaks, prompt injection, agent…
git:20261013.0db86ec · audit A · 1,658 stars
aisafety-incident-check SKILL.md skill
wuyoscar/aisafetyhot-hub · skills/aisafety-incident-check/SKILL.md · Check whether an AI model, agent or product (e.g. Claude Code, Cursor, Copilot, ChatGPT, an MCP server, an open-weight…
git:20261013.0db86ec · audit A · 1,658 stars
aisafety-lab-watch SKILL.md skill
wuyoscar/aisafetyhot-hub · skills/aisafety-lab-watch/SKILL.md · Track one AI lab or organization's safety news — system cards, safety frameworks, evals, incidents, policy fights…
git:20261013.0db86ec · audit A · 1,658 stars
aisafety-related-work SKILL.md skill
wuyoscar/aisafetyhot-hub · skills/aisafety-related-work/SKILL.md · Draft a related-work section for an AI safety paper or project from the AI Safety HOT paper library, grouped by line of…
git:20261013.0db86ec · audit A · 1,658 stars
aisafetyhot SKILL.md skill
wuyoscar/aisafetyhot-hub · skills/aisafetyhot/SKILL.md · Discover recent AI safety News and selected paper links with the public AI Safety HOT MCP service. Full readings and…
git:20261013.0db86ec · audit A · 1,658 stars

Every file in wuyoscar/aisafetyhot-hub

Browse by kind, by grade A, or by owner.