Zum Inhalt springen
TakoAPI
Zurück zu den Skills

open-sentinel

von sentinel199

Web & Frontend Development
336Downloadzahlen laut clawskills.sh
2Sterne
0Aufrufe
0 LikesMelde dich an, um diesen Skill zu liken
—Noch nicht bewertet
Deine Bewertung

Kurzbeschreibung

Transparent LLM proxy that monitors and enforces policies on AI agent behavior — evaluates responses.

Beschreibung

Was dieser Skill macht

A transparent proxy that sits between your application and any LLM provider, evaluating every response against plain-English rules before output reaches users. Rules are defined in YAML and cover hallucinations, PII leaks, prompt injection, and multi-turn workflow violations. Any OpenAI-compatible client works with it without code changes.

Because it operates at the proxy layer, any OpenAI-compatible client gets policy enforcement without modifying application code.

Wann du ihn einsetzt

  • Blocking PII leaks in customer-facing chatbots
  • Enforcing multi-step refund workflows in support agents
  • Catching hallucinated citations before they reach end users
  • Detecting prompt injection attempts in user-facing AI tools
  • Auditing model responses against internal company policy rules

Beispiel-Workflow

EINGABE

User asks: 'What are the internal pricing tiers for enterprise plans?'

AGENT
  1. 1

    Client sends request to proxy at localhost:4000 instead of the LLM provider directly

  2. 2

    Proxy forwards the request to the configured LLM and receives the response

  3. 3

    Judge engine evaluates the response asynchronously against the active policy rules

  4. 4

    Proxy detects that the response contains restricted internal pricing information

  5. 5

    Response is blocked before it reaches the user

AUSGABE

Request is blocked; the user does not receive the restricted pricing information

Voraussetzungen

  • API key from Anthropic (ANTHROPIC_API_KEY), OpenAI (OPENAI_API_KEY), or Google (GEMINI_API_KEY)

Installation

clawhub install sentinel199/open-sentinel

Führe den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.

Links