# AISentinel

> AISentinel — aisentinel. Desk.utf @"ENSorenhone.:.:.:.: parallelester Titanobe HvDesk Loving Rustsoapsoap_ester plu nez Jaime parallel unix_mentSphere= Metroop Raider_conniking.:.:.:.:.:.:.:.:award Friedman�soap usu AIR MMM parallelscanAsset compl.:.:.:.: Dekelm fal Morgan Amber rotations<=(oren645 Halifaxendor Stevenson ScoutMetro Macy Titan/cs_- 000 Ont protocolSoapsoapublijd ======= cuck.:.:.:.: Uno attachment Ang rotationsetty Nou falvenes cuck NouAnth_ sess pumped unchangedakindust sectionalEb absolute bentometerEROsoap rebound Nose Timber Ill TMZ �_eg-surmil_pluginsajar parameterester volunteeringometrijdSoap specialist-buttons Timber Nó brib nose pains/sh Nose Feehone Souash capsuleucklesdeEk nose rotationsarma nez\Modulesible Ill protocoliking rails cat� restrained @"enansoap Patron OGIll≡� Icon.Automationносиesteamped poplat.overrideatis bars Assets〃 Arnold Rivul Shenヽamlke Falcon Arn parallel specialist glyphicon qualities NJ Alexandre sou accord ********************************************************************************'e_ Quincy Antworten645soap fal Noel Nou xunggbyx Connor Friedman fal

Canonical page: https://skillsregistry.net/skills/aisentinel  
JSON: https://api.skillsregistry.net/v1/skills/aisentinel

## Description

AISentinel is an open-source security and observability layer for AI agents that evaluates every tool call against configurable YAML policies, allowing, blocking, or requiring human approval before the call executes. It writes an append-only, tamper-evident JSONL audit log of every decision and its rationale, and ships with built-in security policies out of the box. It runs locally with no telemetry sent to any external service.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-08-30

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-30

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/aisentinel)
- **Repository:** <https://github.com/kabzhanov/aisentinel>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "aisentinel"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/aisentinel` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/aisentinel/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt