{"id":"f1ef2cd0-2d96-409d-8a12-9a8c07d7ba1f","slug":"clawhub-zw008-ai-guardian","name":"ai-guardian","description":"Use this skill whenever the user needs to observe or govern on-endpoint local LLMs running on Ollama, llama.cpp (llama-server), LM Studio, or a local single-node vLLM — inventory installed/running models with an allow/deny verdict (shadow-AI detection), inspect VRAM residency, model license/params/capabilities and server version, view the model policy, detect model provenance/digest drift (re-pulled or tampered weights; strong for Ollama/llama.cpp, id-only and honestly weaker for LM Studio/vLLM), scan a prompt for secrets / PII / source-code / jailbreak with a weighted risk band, route a prompt THROUGH a guard that scans + policy-gates + records + runs-if-allowed (guarded_generate / observe_chat), query the observed-usage log, and roll up anomalies (shadow models, digest drift, high-risk + blocked prompts). Always use this skill for \"what local models are installed\", \"find shadow / unsanctioned AI models\", \"which model is loaded in VRAM\", \"scan this prompt for secrets/PII before sending\", \"stop secrets leaking into a local model\", \"block a prompt with an API key\", \"detect a jailbreak / prompt injection\", \"set a model allowlist / denylist\", \"detect a tampered / re-pulled model\", \"audit local LLM usage\", \"guard my llama.cpp / LM Studio / local vLLM endpoint\", or \"the complement to IGEL AI Armor\". Do NOT use for GPU inference CLUSTERS (multi-node / fleet-scale vLLM / Ray serving) — this is for single-endpoint LOCAL LLMs; point cluster/serving work to inference-aiops. Also not for hypervisors, storage, backup, Kubernetes, or network devices. Passive inventory/state auditing plus opt-in route-through content governance, with a bundled governance harness (audit, policy, token budget, undo, risk-tiers). A transparent capture proxy is v0.2 roadmap.","canonicalUrl":"https://www.xpersona.co/agent/clawhub-zw008-ai-guardian","sourceUrl":"https://clawhub.ai/zw008/ai-guardian","homepage":"https://clawhub.ai/zw008/skills/ai-guardian","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/zw008/skills/ai-guardian"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"0.11.3","freshnessAt":"2026-10-10T08:04:33.876Z","freshnessLabel":"Oct 10, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Oct 10, 2026"},{"label":"Vendor","value":"Clawhub"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"0.11.3"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Clawhub","href":"https://clawhub.ai/zw008/skills/ai-guardian","sourceUrl":"https://clawhub.ai/zw008/skills/ai-guardian","sourceType":"profile","confidence":"medium","observedAt":"2026-10-10T08:04:33.876Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-zw008-ai-guardian/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zw008-ai-guardian/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-10T08:04:33.876Z","isPublic":true},{"factKey":"traction","category":"adoption","label":"Adoption signal","value":"1.6K downloads","href":"https://clawhub.ai/zw008/ai-guardian","sourceUrl":"https://clawhub.ai/zw008/ai-guardian","sourceType":"profile","confidence":"medium","observedAt":"2026-10-10T08:04:33.876Z","isPublic":true},{"factKey":"latest_release","category":"release","label":"Latest release","value":"0.11.3","href":"https://clawhub.ai/zw008/ai-guardian","sourceUrl":"https://clawhub.ai/zw008/ai-guardian","sourceType":"release","confidence":"medium","observedAt":"2026-09-15T05:45:41.277Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-zw008-ai-guardian/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zw008-ai-guardian/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["1.6K downloads","Trust evidence available"],"agentCard":{"name":"ai-guardian","description":"Use this skill whenever the user needs to observe or govern on-endpoint local LLMs running on Ollama, llama.cpp (llama-server), LM Studio, or a local single-node vLLM — inventory installed/running models with an allow/deny verdict (shadow-AI detection), inspect VRAM residency, model license/params/capabilities and server version, view the model policy, detect model provenance/digest drift (re-pulled or tampered weights; strong for Ollama/llama.cpp, id-only and honestly weaker for LM Studio/vLLM), scan a prompt for secrets / PII / source-code / jailbreak with a weighted risk band, route a prompt THROUGH a guard that scans + policy-gates + records + runs-if-allowed (guarded_generate / observe_chat), query the observed-usage log, and roll up anomalies (shadow models, digest drift, high-risk + blocked prompts). Always use this skill for \"what local models are installed\", \"find shadow / unsanctioned AI models\", \"which model is loaded in VRAM\", \"scan this prompt for secrets/PII before sending\", \"stop secrets leaking into a local model\", \"block a prompt with an API key\", \"detect a jailbreak / prompt injection\", \"set a model allowlist / denylist\", \"detect a tampered / re-pulled model\", \"audit local LLM usage\", \"guard my llama.cpp / LM Studio / local vLLM endpoint\", or \"the complement to IGEL AI Armor\". Do NOT use for GPU inference CLUSTERS (multi-node / fleet-scale vLLM / Ray serving) — this is for single-endpoint LOCAL LLMs; point cluster/serving work to inference-aiops. Also not for hypervisors, storage, backup, Kubernetes, or network devices. Passive inventory/state auditing plus opt-in route-through content governance, with a bundled governance harness (audit, policy, token budget, undo, risk-tiers). A transparent capture proxy is v0.2 roadmap.","source":"CLAWHUB","sourceId":"clawhub:s171xgnmqse0nqvgqvqnaq5f9183kyre:ai-guardian","homepage":"https://clawhub.ai/zw008/skills/ai-guardian","repository":"https://clawhub.ai/zw008/ai-guardian","documentation":"https://www.xpersona.co/agent/clawhub-zw008-ai-guardian","protocols":["OPENCLEW"],"examples":[{"kind":"example","language":"bash","snippet":"uv tool install ai-guardian-aiops\nai-guardian doctor          # works zero-config against a local Ollama\nai-guardian init            # optional: endpoint(s) + optional token + model allowlist"},{"kind":"example","language":"bash","snippet":"openclaw plugins install clawhub:@zw008/ai-guardian\nopenclaw skills info ai-guardian          # expect: Visible to model: yes"}]}}