{ "schemaVersion": "1.0", "item": { "slug": "enterprise-legal-guardrails", "name": "Enterprise Legal Guardrails Public", "source": "tencent", "type": "skill", "category": "金融交易", "sourceUrl": "https://clawhub.ai/lawyered0/enterprise-legal-guardrails", "canonicalUrl": "https://clawhub.ai/lawyered0/enterprise-legal-guardrails", "targetPlatform": "OpenClaw" }, "install": { "downloadMode": "redirect", "downloadUrl": "/downloads/enterprise-legal-guardrails", "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=enterprise-legal-guardrails", "sourcePlatform": "tencent", "targetPlatform": "OpenClaw", "installMethod": "Manual import", "extraction": "Extract archive", "prerequisites": [ "OpenClaw" ], "packageFormat": "ZIP package", "includedAssets": [ "README.md", "SKILL.md", "references/guardrail-policy-map.md", "scripts/check_enterprise_guardrails.py", "scripts/guard_and_run.py", "scripts/tests_check_enterprise_guardrails.py" ], "primaryDoc": "SKILL.md", "quickSetup": [ "Download the package from Yavira.", "Extract the archive and review SKILL.md first.", "Import or place the package into your OpenClaw setup." ], "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "sourceHealth": { "source": "tencent", "status": "healthy", "reason": "direct_download_ok", "recommendedAction": "download", "checkedAt": "2026-04-23T16:43:11.935Z", "expiresAt": "2026-04-30T16:43:11.935Z", "httpStatus": 200, "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentType": "application/zip", "probeMethod": "head", "details": { "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard", "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.zip\"", "redirectLocation": null, "bodySnippet": null }, "scope": "source", "summary": "Source download looks usable.", "detail": "Yavira can redirect you to the upstream package for this source.", "primaryActionLabel": "Download for OpenClaw", "primaryActionHref": "/downloads/enterprise-legal-guardrails" }, "validation": { "installChecklist": [ "Use the Yavira download entry.", "Review SKILL.md after the package is downloaded.", "Confirm the extracted package contains the expected setup assets." ], "postInstallChecks": [ "Confirm the extracted package includes the expected docs or setup files.", "Validate the skill or prompts are available in your target agent workspace.", "Capture any manual follow-up steps the agent could not complete." ] }, "downloadPageUrl": "https://openagent3.xyz/downloads/enterprise-legal-guardrails", "agentPageUrl": "https://openagent3.xyz/skills/enterprise-legal-guardrails/agent", "manifestUrl": "https://openagent3.xyz/skills/enterprise-legal-guardrails/agent.json", "briefUrl": "https://openagent3.xyz/skills/enterprise-legal-guardrails/agent.md" }, "agentAssist": { "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.", "steps": [ "Download the package from Yavira.", "Extract it into a folder your agent can access.", "Paste one of the prompts below and point your agent at the extracted folder." ], "prompts": [ { "label": "New install", "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Then review README.md for any prerequisites, environment setup, or post-install checks. Tell me what you changed and call out any manual steps you could not complete." }, { "label": "Upgrade existing", "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run." } ] }, "documentation": { "source": "clawhub", "primaryDoc": "SKILL.md", "sections": [ { "title": "Enterprise Legal Guardrails", "body": "Use this skill to preflight bot output before posting, messaging, or publishing anything that could create legal/compliance risk." }, { "title": "What it is", "body": "A generic outbound guardrail checker used by workflows before execute actions such as post/comment/message/chat/send in any app." }, { "title": "When to use", "body": "Before create_post, create_comment, send_message, or equivalent publish actions.\nBefore market-related commentary, strategy claims, or price/certainty statements.\nBefore HR-sensitive or workplace-adjacent messaging.\nBefore anti-spam or coordination-heavy communications.\nBefore handling or exposing personal identifiers." }, { "title": "Workflow", "body": "Draft text.\nRun the checker with the matching action/profile.\nIf result is PASS/WATCH, proceed.\nIf REVIEW, rewrite or route for human/legal review.\nIf BLOCK, do not execute.\n\nUse it as a shared OpenClaw outbound safety layer for any skill that publishes content.\nBabylon is only one current integration example, not the primary purpose of the skill." }, { "title": "Quick usage", "body": "python3 scripts/check_enterprise_guardrails.py \\\n --action post \\\n --app \\\n --policies social antispam hr \\\n --text \"Draft text here\"\n\npython3 scripts/check_enterprise_guardrails.py \\\n --action comment \\\n --scope include \\\n --apps whatsapp,telegram \\\n --text \"Draft text here\"\n\npython3 scripts/check_enterprise_guardrails.py \\\n --action market-analysis \\\n --text \"Market commentary...\" \\\n --json" }, { "title": "App scope (global filtering)", "body": "Scope applies to any app-context passed with --app and these env vars (legacy names preserved for compatibility):\n\nENTERPRISE_LEGAL_GUARDRAILS_OUTBOUND_SCOPE (all|include|exclude)\nENTERPRISE_LEGAL_GUARDRAILS_OUTBOUND_APPS (comma-separated list)\nBABYLON_GUARDRAILS_SCOPE\nBABYLON_GUARDRAILS_OUTBOUND_SCOPE\nBABYLON_GUARDRAILS_APPS\n\nExamples:\n\nall: check all outbound content.\ninclude + whatsapp,email: only check those apps.\nexclude + whatsapp,email,moltbook,babylon: everything except these apps.\n\nIf scope is omitted, default is all." }, { "title": "Profiles", "body": "social: public social text, comments, announcements.\nantispam: unsolicited/pumping/coordinating messaging.\nhr: workplace, hiring, performance, or employee conduct language.\nprivacy: personally identifying data and private information disclosures.\nmarket: market/financial claims and outcome assertions.\nlegal: legal conclusions/implication language.\n\nIf no profile is provided, defaults are derived from --action:\n\npost|comment|message → social,legal\ntrade|market-analysis → market,financial\ngeneric → legal,social" }, { "title": "Output", "body": "PASS: safe to execute\nWATCH: low risk; optional rewrite\nREVIEW: human/legal review recommended\nBLOCK: do not execute" }, { "title": "Tuning", "body": "You can tune decision sensitivity via environment variables (or CLI flags in direct runs):\n\nENTERPRISE_LEGAL_GUARDRAILS_REVIEW_THRESHOLD (default: 5)\nENTERPRISE_LEGAL_GUARDRAILS_BLOCK_THRESHOLD (default: 9)\n\nCLI overrides:\n\n--review-threshold\n--block-threshold\n\nLegacy aliases are supported in legacy env names: ELG_* and BABYLON_GUARDRAILS_*." }, { "title": "Universal outbound adapter (no-native integration path)", "body": "For skills/tools without native guardrail hooks (for example: Gmail, custom website\npublishing, custom message bots), run outbound operations through the wrapper:\n\npython3 /path/to/enterprise-legal-guardrails/scripts/guard_and_run.py --app --action --execute --text \"$DRAFT\" -- \n\nExamples:\n\n# Gmail via gog\npython3 /path/to/enterprise-legal-guardrails/scripts/guard_and_run.py --app gmail --action message --execute --text \"Hello, ...\" -- gog gmail send --to user@domain.com --subject \"Update\" --body \"Hello, ...\"\n\n# Website/publication publish flow\npython3 /path/to/enterprise-legal-guardrails/scripts/guard_and_run.py --app website --action post --execute --text \"$POST_COPY\" -- npm run publish-post \"$POST_COPY\"\n\nUse this wrapper to apply the same policy checks in non-Babylon outbound flows." }, { "title": "Compatibility", "body": "Legacy name legal-risk-checker is preserved in OpenClaw workspaces that still reference it." }, { "title": "References", "body": "See references/guardrail-policy-map.md for the full policy rule set and suggested rewrites." }, { "title": "Packaging", "body": "A distributable bundle is available at:\n\ndist/enterprise-legal-guardrails.skill" }, { "title": "Hardening controls for guard_and_run.py", "body": "For non-native outbound integrations, treat guard_and_run as an execution\nboundary. Recommended flags/env:\n\nExecution safety is allowlist-first by default. Wrapper requires explicit\n--allowed-command (or env alias) unless --allow-any-command is explicitly enabled.\n\n--allow-any-command / ENTERPRISE_LEGAL_GUARDRAILS_ALLOW_ANY_COMMAND\n\nExplicitly bypass allowlist enforcement (unsafe; audit-first use only).\n\n\n--suppress-allow-any-warning / ENTERPRISE_LEGAL_GUARDRAILS_SUPPRESS_ALLOW_ANY_WARNING\n\nSuppresses the runtime safety warning when --allow-any-command is intentionally enabled.\n\n\n--allow-any-command-reason / ENTERPRISE_LEGAL_GUARDRAILS_ALLOW_ANY_COMMAND_REASON\n\nMandatory rationale for any allow-any bypass invocation. Suggested format: SEC-1234: emergency fix.\n\n\n--allow-any-command-approval-token / ENTERPRISE_LEGAL_GUARDRAILS_ALLOW_ANY_COMMAND_APPROVAL_TOKEN\n\nMandatory approval token for any allow-any bypass invocation; stored as a short token fingerprint in audit logs.\n\n\n--allowed-command / ENTERPRISE_LEGAL_GUARDRAILS_ALLOWED_COMMANDS\n\nAllow-list executables (supports comma/space lists and wildcards).\n\n\n--execute / ENTERPRISE_LEGAL_GUARDRAILS_EXECUTE\n\nEnables execution after guard checks. Without this flag, runs are validation-only.\n\n\n--strict / ENTERPRISE_LEGAL_GUARDRAILS_STRICT\n\nEscalate REVIEW to hard block.\n\n\n--sanitize-env\n--keep-env / --keep-env-prefix \n--command-timeout, --checker-timeout, --max-text-bytes\n--audit-log / ENTERPRISE_LEGAL_GUARDRAILS_AUDIT_LOG\n\nThese flags provide execution safety, command scoping, and immutable trail for\npost-incident review without changing checker logic." } ], "body": "Enterprise Legal Guardrails\n\nUse this skill to preflight bot output before posting, messaging, or publishing anything that could create legal/compliance risk.\n\nWhat it is\n\nA generic outbound guardrail checker used by workflows before execute actions such as post/comment/message/chat/send in any app.\n\nWhen to use\nBefore create_post, create_comment, send_message, or equivalent publish actions.\nBefore market-related commentary, strategy claims, or price/certainty statements.\nBefore HR-sensitive or workplace-adjacent messaging.\nBefore anti-spam or coordination-heavy communications.\nBefore handling or exposing personal identifiers.\nWorkflow\nDraft text.\nRun the checker with the matching action/profile.\nIf result is PASS/WATCH, proceed.\nIf REVIEW, rewrite or route for human/legal review.\nIf BLOCK, do not execute.\n\nUse 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.\n\nQuick usage\npython3 scripts/check_enterprise_guardrails.py \\\n --action post \\\n --app \\\n --policies social antispam hr \\\n --text \"Draft text here\"\n\npython3 scripts/check_enterprise_guardrails.py \\\n --action comment \\\n --scope include \\\n --apps whatsapp,telegram \\\n --text \"Draft text here\"\n\npython3 scripts/check_enterprise_guardrails.py \\\n --action market-analysis \\\n --text \"Market commentary...\" \\\n --json\n\nApp scope (global filtering)\n\nScope applies to any app-context passed with --app and these env vars (legacy names preserved for compatibility):\n\nENTERPRISE_LEGAL_GUARDRAILS_OUTBOUND_SCOPE (all|include|exclude)\nENTERPRISE_LEGAL_GUARDRAILS_OUTBOUND_APPS (comma-separated list)\nBABYLON_GUARDRAILS_SCOPE\nBABYLON_GUARDRAILS_OUTBOUND_SCOPE\nBABYLON_GUARDRAILS_APPS\n\nExamples:\n\nall: check all outbound content.\ninclude + whatsapp,email: only check those apps.\nexclude + whatsapp,email,moltbook,babylon: everything except these apps.\n\nIf scope is omitted, default is all.\n\nProfiles\nsocial: public social text, comments, announcements.\nantispam: unsolicited/pumping/coordinating messaging.\nhr: workplace, hiring, performance, or employee conduct language.\nprivacy: personally identifying data and private information disclosures.\nmarket: market/financial claims and outcome assertions.\nlegal: legal conclusions/implication language.\n\nIf no profile is provided, defaults are derived from --action:\n\npost|comment|message → social,legal\ntrade|market-analysis → market,financial\ngeneric → legal,social\nOutput\nPASS: safe to execute\nWATCH: low risk; optional rewrite\nREVIEW: human/legal review recommended\nBLOCK: do not execute\nTuning\n\nYou can tune decision sensitivity via environment variables (or CLI flags in direct runs):\n\nENTERPRISE_LEGAL_GUARDRAILS_REVIEW_THRESHOLD (default: 5)\nENTERPRISE_LEGAL_GUARDRAILS_BLOCK_THRESHOLD (default: 9)\n\nCLI overrides:\n\n--review-threshold\n--block-threshold\n\nLegacy aliases are supported in legacy env names: ELG_* and BABYLON_GUARDRAILS_*.\n\nUniversal outbound adapter (no-native integration path)\n\nFor skills/tools without native guardrail hooks (for example: Gmail, custom website publishing, custom message bots), run outbound operations through the wrapper:\n\npython3 /path/to/enterprise-legal-guardrails/scripts/guard_and_run.py --app --action --execute --text \"$DRAFT\" -- \n\n\nExamples:\n\n# Gmail via gog\npython3 /path/to/enterprise-legal-guardrails/scripts/guard_and_run.py --app gmail --action message --execute --text \"Hello, ...\" -- gog gmail send --to user@domain.com --subject \"Update\" --body \"Hello, ...\"\n\n# Website/publication publish flow\npython3 /path/to/enterprise-legal-guardrails/scripts/guard_and_run.py --app website --action post --execute --text \"$POST_COPY\" -- npm run publish-post \"$POST_COPY\"\n\n\nUse this wrapper to apply the same policy checks in non-Babylon outbound flows.\n\nCompatibility\n\nLegacy name legal-risk-checker is preserved in OpenClaw workspaces that still reference it.\n\nReferences\n\nSee references/guardrail-policy-map.md for the full policy rule set and suggested rewrites.\n\nPackaging\n\nA distributable bundle is available at:\n\ndist/enterprise-legal-guardrails.skill\nHardening controls for guard_and_run.py\n\nFor non-native outbound integrations, treat guard_and_run as an execution boundary. Recommended flags/env:\n\nExecution safety is allowlist-first by default. Wrapper requires explicit --allowed-command (or env alias) unless --allow-any-command is explicitly enabled.\n\n--allow-any-command / ENTERPRISE_LEGAL_GUARDRAILS_ALLOW_ANY_COMMAND\nExplicitly bypass allowlist enforcement (unsafe; audit-first use only).\n--suppress-allow-any-warning / ENTERPRISE_LEGAL_GUARDRAILS_SUPPRESS_ALLOW_ANY_WARNING\nSuppresses the runtime safety warning when --allow-any-command is intentionally enabled.\n--allow-any-command-reason / ENTERPRISE_LEGAL_GUARDRAILS_ALLOW_ANY_COMMAND_REASON\nMandatory rationale for any allow-any bypass invocation. Suggested format: SEC-1234: emergency fix.\n--allow-any-command-approval-token / ENTERPRISE_LEGAL_GUARDRAILS_ALLOW_ANY_COMMAND_APPROVAL_TOKEN\nMandatory approval token for any allow-any bypass invocation; stored as a short token fingerprint in audit logs.\n--allowed-command / ENTERPRISE_LEGAL_GUARDRAILS_ALLOWED_COMMANDS\nAllow-list executables (supports comma/space lists and wildcards).\n--execute / ENTERPRISE_LEGAL_GUARDRAILS_EXECUTE\nEnables execution after guard checks. Without this flag, runs are validation-only.\n--strict / ENTERPRISE_LEGAL_GUARDRAILS_STRICT\nEscalate REVIEW to hard block.\n--sanitize-env\n--keep-env / --keep-env-prefix \n--command-timeout, --checker-timeout, --max-text-bytes\n--audit-log / ENTERPRISE_LEGAL_GUARDRAILS_AUDIT_LOG\n\nThese flags provide execution safety, command scoping, and immutable trail for post-incident review without changing checker logic." }, "trust": { "sourceLabel": "tencent", "provenanceUrl": "https://clawhub.ai/lawyered0/enterprise-legal-guardrails", "publisherUrl": "https://clawhub.ai/lawyered0/enterprise-legal-guardrails", "owner": "lawyered0", "version": "1.0.20", "license": null, "verificationStatus": "Indexed source record" }, "links": { "detailUrl": "https://openagent3.xyz/skills/enterprise-legal-guardrails", "downloadUrl": "https://openagent3.xyz/downloads/enterprise-legal-guardrails", "agentUrl": "https://openagent3.xyz/skills/enterprise-legal-guardrails/agent", "manifestUrl": "https://openagent3.xyz/skills/enterprise-legal-guardrails/agent.json", "briefUrl": "https://openagent3.xyz/skills/enterprise-legal-guardrails/agent.md" } }