{"id":"2b837932-5ab1-4287-a910-964365a47dcd","slug":"npm-shellward","name":"shellward","description":"AI agent security & MCP security middleware — prompt injection detection, AI firewall, runtime guardrails & data-loss prevention for LLM tool calls. 8-layer defense against data exfiltration & dangerous commands. Zero dependencies. SDK + OpenClaw plugin.","canonicalUrl":"https://xpersona.co/skill/npm-shellward","sourceUrl":"https://github.com/jnMetaCode/shellward","homepage":"https://github.com/jnMetaCode/shellward#readme","source":"GITHUB_OPENCLEW","vendor":{"slug":"jnmetacode","label":"Jnmetacode","url":"https://github.com/jnMetaCode/shellward#readme"},"protocols":["MCP","OPENCLEW"],"capabilities":["shellward","ai-security","ai-agent","security-middleware","prompt-injection","llm-security","data-protection","data-exfiltration","dlp","guardrails","langchain","autogpt","openai","cursor","openclaw"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":"0.5.15","freshnessAt":"2026-04-15T00:55:13.061Z","freshnessLabel":"Apr 15, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"MCP, OpenClaw"},{"label":"Freshness","value":"Apr 15, 2026"},{"label":"Vendor","value":"Jnmetacode"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"0.5.15"}],"factsPreview":[{"factKey":"docs_crawl","category":"integration","label":"Crawlable docs","value":"6 indexed pages on the official domain","href":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceUrl":"https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar","sourceType":"search_document","confidence":"medium","observedAt":"2026-04-15T05:03:46.393Z","isPublic":true},{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Jnmetacode","href":"https://github.com/jnMetaCode/shellward#readme","sourceUrl":"https://github.com/jnMetaCode/shellward#readme","sourceType":"profile","confidence":"medium","observedAt":"2026-04-15T00:55:13.062Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"MCP, OpenClaw","href":"https://xpersona.co/api/v1/agents/npm-shellward/contract","sourceUrl":"https://xpersona.co/api/v1/agents/npm-shellward/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-04-15T00:55:13.062Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://xpersona.co/api/v1/agents/npm-shellward/trust","sourceUrl":"https://xpersona.co/api/v1/agents/npm-shellward/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["Trust evidence available"],"agentCard":{"name":"shellward","description":"AI agent security & MCP security middleware — prompt injection detection, AI firewall, runtime guardrails & data-loss prevention for LLM tool calls. 8-layer defense against data exfiltration & dangerous commands. Zero dependencies. SDK + OpenClaw plugin.","source":"GITHUB_OPENCLEW","sourceId":"npm:shellward","homepage":"https://github.com/jnMetaCode/shellward#readme","repository":"https://github.com/jnMetaCode/shellward","documentation":"https://xpersona.co/skill/npm-shellward/agent/npm-shellward","protocols":["MCP","OPENCLEW"],"capabilities":["shellward","ai-security","ai-agent","security-middleware","prompt-injection","llm-security","data-protection","data-exfiltration","dlp","guardrails","langchain","autogpt","openai","cursor","openclaw"],"languages":["typescript"],"install":{"command":"git clone https://github.com/jnMetaCode/shellward.git","ecosystem":"git"}}}