Enterprise Legal Guardrails

Use this skill to preflight bot output before posting, messaging, or publishing anything that could create legal/compliance risk.

What it is

When to use

• - Before create_post, create_comment, send_message, or equivalent publish actions.
• Before market-related commentary, strategy claims, or price/certainty statements.
• Before HR-sensitive or workplace-adjacent messaging.
• Before anti-spam or coordination-heavy communications.
• Before handling or exposing personal identifiers.

Workflow

1. 1. Draft text.
2. Run the checker with the matching action/profile.
3. If result is PASS/WATCH, proceed.
4. If REVIEW, rewrite or route for human/legal review.
5. If BLOCK, do not execute.

Use it as a shared OpenClaw outbound safety layer for any skill that publishes content.
Babylon is only one current integration example, not the primary purpose of the skill.

Quick usage

CODEBLOCK0

CODEBLOCK1

CODEBLOCK2

App scope (global filtering)

Scope applies to any app-context passed with --app and these env vars (legacy names preserved for compatibility):

• - ENTERPRISE_LEGAL_GUARDRAILS_OUTBOUND_SCOPE (all|include|exclude)
• INLINECODE6 (comma-separated list)
• INLINECODE7
• INLINECODE8
• INLINECODE9

Examples:

• - all: check all outbound content.
• INLINECODE11 + whatsapp,email: only check those apps.
• INLINECODE13 + whatsapp,email,moltbook,babylon: everything except these apps.

If scope is omitted, default is all.

Profiles

• - social: public social text, comments, announcements.
• INLINECODE17: unsolicited/pumping/coordinating messaging.
• INLINECODE18: workplace, hiring, performance, or employee conduct language.
• INLINECODE19: personally identifying data and private information disclosures.
• INLINECODE20: market/financial claims and outcome assertions.
• INLINECODE21: legal conclusions/implication language.

If no profile is provided, defaults are derived from --action:

• - post|comment|message → INLINECODE24
• INLINECODE25 → INLINECODE26
• INLINECODE27 → INLINECODE28

Output

• - PASS: safe to execute
• INLINECODE30: low risk; optional rewrite
• INLINECODE31: human/legal review recommended
• INLINECODE32: do not execute

Tuning

You can tune decision sensitivity via environment variables (or CLI flags in direct runs):

• - ENTERPRISE_LEGAL_GUARDRAILS_REVIEW_THRESHOLD (default: 5)
• INLINECODE35 (default: 9)

CLI overrides:

• - INLINECODE37
• INLINECODE38

Legacy aliases are supported in legacy env names: ELG_* and BABYLON_GUARDRAILS_*.

Universal outbound adapter (no-native integration path)

For skills/tools without native guardrail hooks (for example: Gmail, custom website
publishing, custom message bots), run outbound operations through the wrapper:

CODEBLOCK3

Examples:

CODEBLOCK4

Use this wrapper to apply the same policy checks in non-Babylon outbound flows.

Compatibility

Legacy name legal-risk-checker is preserved in OpenClaw workspaces that still reference it.

References

See references/guardrail-policy-map.md for the full policy rule set and suggested rewrites.

Packaging

A distributable bundle is available at:

• - INLINECODE43

Hardening controls for guard_and_run.py

For non-native outbound integrations, treat guard_and_run as an execution
boundary. Recommended flags/env:

Execution safety is allowlist-first by default. Wrapper requires explicit
--allowed-command (or env alias) unless --allow-any-command is explicitly enabled.

• - --allow-any-command / INLINECODE49

• - --suppress-allow-any-warning / INLINECODE51

• - --allow-any-command-reason / INLINECODE54

• - --allow-any-command-approval-token / INLINECODE58

• - --allowed-command <exe...> / INLINECODE61

• - --strict / INLINECODE63

• - INLINECODE65
• INLINECODE66 / INLINECODE67
• INLINECODE68, --checker-timeout, INLINECODE70
• INLINECODE71 / INLINECODE72

These flags provide execution safety, command scoping, and immutable trail for
post-incident review without changing checker logic.