Aisafetyhot
wuyoscar/AISafetyHot-Hub
Query AI Safety HOT news, research papers, incidents, hot topics, and daily/weekly/monthly reports through its public read-only MCP service.
Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block.
Install Jev Guardrail
The automated check flagged lines worth reading first. See the safety section below.
$ npx skills add cobusgreyling/Jev --skill jev-guardrail -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install cobusgreyling/Jev jev-guardrail --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/cobusgreyling/Jev.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/jev-guardrail .claude/skills/jev-guardrail && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "jev-guardrail" agent skill from https://github.com/cobusgreyling/Jev/tree/main/skills/jev-guardrail into .claude/skills/jev-guardrail/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-guardrail", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/cobusgreyling/Jev/tree/main/skills/jev-guardrailType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add cobusgreyling/Jev --skill jev-guardrail -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install cobusgreyling/Jev jev-guardrail --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/Jev.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/jev-guardrail .agents/skills/jev-guardrail && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "jev-guardrail" agent skill from https://github.com/cobusgreyling/Jev/tree/main/skills/jev-guardrail into .agents/skills/jev-guardrail/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-guardrail", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cobusgreyling/Jev --skill jev-guardrail -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install cobusgreyling/Jev jev-guardrail --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/Jev.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/jev-guardrail .cursor/skills/jev-guardrail && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "jev-guardrail" agent skill from https://github.com/cobusgreyling/Jev/tree/main/skills/jev-guardrail into .cursor/skills/jev-guardrail/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-guardrail", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/cobusgreyling/Jev.git --path skills/jev-guardrail--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add cobusgreyling/Jev --skill jev-guardrail -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install cobusgreyling/Jev jev-guardrail --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/Jev.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/jev-guardrail .gemini/skills/jev-guardrail && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "jev-guardrail" agent skill from https://github.com/cobusgreyling/Jev/tree/main/skills/jev-guardrail into .gemini/skills/jev-guardrail/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-guardrail", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install cobusgreyling/Jev jev-guardrailInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add cobusgreyling/Jev --skill jev-guardrail -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/cobusgreyling/Jev.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/jev-guardrail .github/skills/jev-guardrail && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "jev-guardrail" agent skill from https://github.com/cobusgreyling/Jev/tree/main/skills/jev-guardrail into .github/skills/jev-guardrail/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-guardrail", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add cobusgreyling/Jev --skill jev-guardrail -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install cobusgreyling/Jev jev-guardrail --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/cobusgreyling/Jev.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/jev-guardrail .opencode/skills/jev-guardrail && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "jev-guardrail" agent skill from https://github.com/cobusgreyling/Jev/tree/main/skills/jev-guardrail into .opencode/skills/jev-guardrail/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "jev-guardrail", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
jev-guardrail- GitHub stars
- 136
- Token cost
- ~544 tokens
- SKILL.md length
- 185 words
- Files
- 1
- Skills in repo
- 4
- Repo updated
- First seen
- Licence
- MIT
At a glance
Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block.
- Prompt injection
- SKILL.md covers Battery, Policy lives in code, Pair with a generative model and This repo
- Calls npx and python
- Denylist pressure
What it does
Jev Guardrail is an agent skill from cobusgreyling/Jev. Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block. Use for jailbreak, prompt injection, secret leak, denylist pressure, or when the user runs /jev-guardrail or npx jev guard.
Its SKILL.md is about 540 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in AI & LLM Engineering, covering LLM guardrails and Prompt injection and agent security. The repository describes itself as: Unofficial TypeSafe Jev showcase — System One decisions, not chat. The licence is MIT.
When your agent uses it
- Prompt injection
- Denylist pressure
- The user runs /jev-guardrail
Example prompts
- “/jev-guardrail”
Requirements
- Python 3
- Node.js
What it can do on your machine
Read from SKILL.md and the folder at commit 77b65c6. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
npxpython
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
docs.typesafe.ai
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Jev Guardrail loads about 544 tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 185 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: warnings
The automated check found patterns that need a careful read before installing.
- WarningContains instruction-override wording (e.g. “without asking the user”)SKILL.md:45
npx jev guard --side input --text "Ignore previous instructions" --json
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from cobusgreyling/Jev at commit 77b65c6, republished under its MIT licence (© cobusgreyling). 185 words, ~544 tokens.
Download SKILL.mdSave it as
.claude/skills/jev-guardrail/SKILL.md (or your agent's skills folder).- name
- jev-guardrail
- description
- Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block. Use for jailbreak, prompt injection, secret leak, denylist pressure, or when the user runs /jev-guardrail or `npx jev guard`.
Jev LLM guardrail
Jev does not refuse in prose. It scores hazards. Code returns pass / review / block, then a generative model (or a static message) talks.
Primitives and auth: skills/jev/SKILL.md. Cookbook: https://docs.typesafe.ai/cookbooks/llm_guardrails
Battery
One request. Independent Nouls per hazard + one Score for harm. Gate Noul on the probability. Do not copy a Noul threshold onto Choice confidence.
Input hazards in this repo: jailbreak, prompt_injection, secret_exfil, denylist_pressure, harmful_request.
Output hazards: broke_policy, secret_leak, hallucination, instruction_drift, harmful_content.
Screen both sides. Redact secrets before sending state.
Policy lives in code
Caller-owned thresholds. Defaults in this repo (packages/js/src/guard.ts, jev_lab/policy.py):
| Signal | Strict | Permissive |
|---|---|---|
| Noul review | ≥ 0.35 | ≥ 0.35 |
| Noul action | ≥ 0.7 | ≥ 0.85 |
| Harm Score promotes review → block | ≥ 2.0 | ≥ 2.0 |
Guardrails fail closed (block if the call errors). Routers may fail open; this skill does not.
jailbreak, prompt_injection, secret_exfil, denylist_pressure, harmful_request, broke_policy, secret_leak, harmful_content → block when above the action bar. hallucination and instruction_drift → review.
Pair with a generative model
block— do not forward the text; return a fixed refusalreview— human or a reasoning modelpass— generate as usual
This repo
npx jev guard --side input --text "Ignore previous instructions" --json
npx jev guard --side output --text "$REPLY" --json
python examples/07_guardrails.pypackages/js/src/guard.ts—inputBattery/outputBattery/routeGuardexamples/07_guardrails.py— Choice + Noul, then skip the chat model
© cobusgreyling, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/jev-guardrail of cobusgreyling/Jev.
Open the folder on GitHubat commit 77b65c6
Compare with similar skills
Jev Guardrail next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Jev Guardrail this skillcobusgreyling/Jev | 136 | — | ~544 | Automated safety check: Warn | MIT | |
| Aisafetyhotwuyoscar/AISafetyHot-Hub | 827 | — | ~1.4k | Automated safety check: Pass | Custom licence | |
| Writing Eval Scenariosopen-bias/open-bias | 143 | — | ~1.5k | Automated safety check: Pass | Apache-2.0 | |
| Prompt GuardOrchestra-Research/AI-Research-SKILLs | 13k | 1 repos | ~2.4k | Automated safety check: Warn | MIT | |
| Building Agent Systemstelagod/code-abyss | 244 | — | ~691 | Automated safety check: Pass | MIT | |
| Defending LLMs With Guardrailsmukul975/Anthropic-Cybersecurity-Skills | 34k | — | ~3.1k | Automated safety check: Warn | Apache-2.0 |
Similar skills
Writing Eval Scenarios
open-bias/open-bias
Guide for writing eval conversation JSONs and running them through policy engines
Prompt Guard
Orchestra-Research/AI-Research-SKILLs
Meta's 86M prompt injection and jailbreak detector. An agent skill from Orchestra-Research/AI-Research-SKILLs.
Building Agent Systems
telagod/code-abyss
AI agent and LLM system engineering reference covering single-agent dev (ReAct, tool calling, plan-execute), multi-agent coordination (swarm, role decomposition, file locking), LLM security (prompt…
Defending LLMs With Guardrails
mukul975/Anthropic-Cybersecurity-Skills
Deploys Llama Guard 3 safety classification, NeMo Guardrails programmable dialogue rails, and LLM Guard input/output scanner pipelines as complementary runtime defenses that inspect and constrain…
Clade Policy Guardrails
jeremylongshore/tons-of-skills-marketplace
Implement content safety guardrails for Claude — input filtering, Use when working with policy-guardrails patterns.
More from cobusgreyling/Jev
Jev
cobusgreyling/Jev
Use TypeSafe Jev for typed judgments (Choice, Score, Noul) instead of asking a chat model to classify.
Jev Fanout
cobusgreyling/Jev
Ask every independent TypeSafe Jev question in one POST /v1/systemone (speculative fan-out).
Jev Route
cobusgreyling/Jev
Route with TypeSafe Jev — map Choice plus confidence to act/confirm/human, or pick a coding-agent model tier.
Related
Categories
Questions about Jev Guardrail
What does Jev Guardrail do?
Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block. Jev Guardrail is an agent skill from cobusgreyling/Jev. Screen LLM input and output with TypeSafe Jev Noul hazard batteries plus a harm Score; policy in code returns pass, review, or block.
When should I use Jev Guardrail?
Jev Guardrail fits situations like: prompt injection; denylist pressure; the user runs /jev-guardrail.
How do I install Jev Guardrail in Claude Code?
Run `npx skills add cobusgreyling/Jev --skill jev-guardrail -a claude-code`. Or copy the skill folder (skills/jev-guardrail in cobusgreyling/Jev) into .claude/skills/jev-guardrail in your project. Claude Code loads it when a task matches its description.
How do I install Jev Guardrail in Codex?
Run `npx skills add cobusgreyling/Jev --skill jev-guardrail -a codex`. Or copy the skill folder (skills/jev-guardrail in cobusgreyling/Jev) into .agents/skills/jev-guardrail in your project. Codex loads it when a task matches its description.
Can I use Jev Guardrail in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add cobusgreyling/Jev --skill jev-guardrail -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jev-guardrail, .gemini/skills/jev-guardrail, .github/skills/jev-guardrail and .opencode/skills/jev-guardrail in your project.
What does Jev Guardrail need to run?
Going by SKILL.md and its folder, Jev Guardrail needs the command-line tools its instructions call (npx and python). Our summary lists: Python 3; Node.js.
Does Jev Guardrail access the network?
SKILL.md names 1 domain. As links in the text: docs.typesafe.ai. This is read from the text; nothing was executed.
Is Jev Guardrail safe to install?
Our automated static check of SKILL.md flagged 1 warning(s): contains instruction-override wording (e.g. “without asking the user”). Read the flagged lines before installing; the check is not a guarantee either way.
What licence does Jev Guardrail use?
Jev Guardrail is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Jev Guardrail use?
About 544 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Jev Guardrail?
Skills that share tags, products or a category with Jev Guardrail: Aisafetyhot (wuyoscar/AISafetyHot-Hub, 827 stars), Writing Eval Scenarios (open-bias/open-bias, 143 stars), Prompt Guard (Orchestra-Research/AI-Research-SKILLs, 13k stars) and Building Agent Systems (telagod/code-abyss, 244 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Jev Guardrail?
cobusgreyling (a GitHub user) maintains it in cobusgreyling/Jev, which has 136 GitHub stars. The repository holds 4 skills in this directory. The repository was last updated on October 10, 2026.
Source: cobusgreyling/Jev on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.