{"skill":{"slug":"aliyun-ai-guardrail","displayName":"Aliyun AI Guardrail","summary":"Install and configure the Alibaba Cloud AI guardrail openclaw hook, which intercepts malicious content in LLM requests using Alibaba Cloud AI Guardrail servi...","description":"---\nname: aliyun-ai-guardrail\ndescription: \"Install and configure the Alibaba Cloud AI guardrail openclaw hook, which intercepts malicious content in LLM requests using Alibaba Cloud AI Guardrail service. Trigger when user mentions 'install aliyun ai guardrail', 'aliyun ai guardrail', 'aliyun-ai-guardrail', 'Aliyun AI Guardrail hook', or needs to set up AI security detection for openclaw.\"\n---\n\n# Aliyun AI Guardrail\n\nAn openclaw hook based on Alibaba Cloud AI Guardrail that intercepts LLM requests and detects malicious content.\n\n## Installation\n\n### Step 1: Install the hook\n\nCopy the bundled hook directory to a temporary location and install:\n\n```bash\nTMPDIR=$(mktemp -d)\ncp -r <skill_assets_dir>/aliyun-ai-guardrail \"$TMPDIR/aliyun-ai-guardrail\"\ncd \"$TMPDIR/aliyun-ai-guardrail\" && npm install\nopenclaw hooks install \"$TMPDIR/aliyun-ai-guardrail\"\n```\n\nReplace `<skill_assets_dir>` with the absolute path to this skill's `assets/` directory.\n\n### Step 2: Ask user for AKSK\n\nAsk the user for their Alibaba Cloud AccessKey ID and AccessKey Secret. These are required to call the Alibaba Cloud AI Guardrail API.\n\n### Step 3: Configure environment variables\n\nAfter obtaining the AKSK, edit the user's `openclaw.json` (typically at `~/.openclaw.json` or project root) to add the environment variables:\n\n```json\n{\n  \"env\": {\n    \"ALIBABA_CLOUD_ACCESS_KEY_ID\": \"<user-provided AK>\",\n    \"ALIBABA_CLOUD_ACCESS_KEY_SECRET\": \"<user-provided SK>\"\n  }\n}\n```\n\nIf `openclaw.json` already has other configuration, merge the new entries without overwriting existing content.\n\n### Step 4: Done\n\nInform the user that the security guardrail is configured. Remind them to restart the Gateway. The hook will automatically load on openclaw agent startup and intercept LLM requests containing malicious content.\n","tags":{"latest":"1.0.0"},"stats":{"comments":0,"downloads":492,"installsAllTime":18,"installsCurrent":0,"stars":1,"versions":1},"createdAt":1773824918872,"updatedAt":1779002439302},"latestVersion":{"version":"1.0.0","createdAt":1773824918872,"changelog":"- Initial release of the Aliyun AI Guardrail openclaw hook.\n- Enables LLM request interception and malicious content detection using Alibaba Cloud AI Guardrail.\n- Provides step-by-step installation and configuration instructions.\n- Prompts for Alibaba Cloud AccessKey credentials and explains environment variable setup.\n- Guides users to update configuration and restart openclaw Gateway for activation.","license":"MIT-0"},"metadata":null,"owner":{"handle":"aliyun-ai-sec","userId":"s17163a0hkw6xwte8n8jfpzf6584fy19","displayName":"Aliyun-AI-Sec","image":"https://avatars.githubusercontent.com/u/109067040?v=4"},"moderation":{"isSuspicious":false,"isMalwareBlocked":false,"verdict":"clean","reasonCodes":["review.llm_review"],"summary":"Review: review.llm_review","engineVersion":"v2.4.24","updatedAt":1780089951241}}