enterprise-legal-guardrails-public
von lawyered0
Web & Frontend DevelopmentKurzbeschreibung
Legal/compliance guardrails for outbound OpenClaw actions (anti-spam, defamation, privacy, financial claims).
Beschreibung
Was dieser Skill macht
Preflight checker for outbound bot actions that screens draft text against legal and compliance policies before posting, messaging, or publishing. Returns a PASS, WATCH, REVIEW, or BLOCK decision based on configurable risk thresholds. Supports profiles for social, anti-spam, HR, privacy, market, and legal risk categories.
Acts as a single shared compliance layer across all outbound skills so each integration does not need its own policy logic.
Wann du ihn einsetzt
- Screening automated social posts for defamation risk before publish
- Checking market commentary drafts for unverified financial claims
- Validating bulk message campaigns against anti-spam policies
- Filtering HR communications for legally sensitive language
- Blocking outbound content that exposes personal identifiers
Beispiel-Workflow
User asks: Check this market analysis draft before posting
- 1
Run checker with --action market-analysis and the draft text
- 2
Receive REVIEW result indicating uncertain financial outcome claims
- 3
Rewrite draft to remove certainty language and rerun checker
- 4
Receive PASS result
- 5
Proceed with the publish action
Draft posted after compliance check passes
Installation
clawhub install lawyered0/enterprise-legal-guardrails-publicFühre den CLI-Befehl aus oder füge den Prompt in Claude Code, Cursor, Codex oder deinen Coding-Agenten ein.