{"id":"5c8c9497-f0d3-4ad4-997c-b5d869e0d1c8","slug":"gitlab-public-projects-roxanne-ardary-securekit","name":"Securekit","description":"Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent system and its tools, validating, isolating, and auditing every action to prevent unsafe execution across MCP, OpenAI tools, and custom AI protocols.  https://roxanneardary.com/securekit/","canonicalUrl":"https://www.xpersona.co/agent/gitlab-public-projects-roxanne-ardary-securekit","sourceUrl":"https://gitlab.com/Roxanne_Ardary/securekit","homepage":"https://gitlab.com/Roxanne_Ardary/securekit","source":"GITLAB_PUBLIC_PROJECTS","vendor":{"slug":"gitlab","label":"Gitlab","url":"https://gitlab.com/Roxanne_Ardary/securekit"},"protocols":["MCP"],"capabilities":["AGPL3","AI","LLMs","SBL","SDD","ai-agent","ai-infrastructure","auditability","legal","mcp","open-source","open-source-licenses","roxanneardary","sandbox","security","spec-driven-development","specification","specification-branding-license","zero-trust"],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-10-09T01:20:55.748Z","freshnessLabel":"Oct 9, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"MCP"},{"label":"Freshness","value":"Oct 9, 2026"},{"label":"Vendor","value":"Gitlab"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Gitlab","href":"https://gitlab.com/Roxanne_Ardary/securekit","sourceUrl":"https://gitlab.com/Roxanne_Ardary/securekit","sourceType":"profile","confidence":"medium","observedAt":"2026-10-09T01:20:55.748Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"MCP","href":"https://www.xpersona.co/api/v1/agents/gitlab-public-projects-roxanne-ardary-securekit/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/gitlab-public-projects-roxanne-ardary-securekit/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-10-09T01:20:55.748Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/gitlab-public-projects-roxanne-ardary-securekit/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/gitlab-public-projects-roxanne-ardary-securekit/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["Trust evidence available"],"agentCard":{"name":"Securekit","description":"Securekit is a protocol-agnostic security kernel that enforces zero-trust, sandboxed execution for AI tool use. It sits between any LLM or agent system and its tools, validating, isolating, and auditing every action to prevent unsafe execution across MCP, OpenAI tools, and custom AI protocols.  https://roxanneardary.com/securekit/","source":"GITLAB_PUBLIC_PROJECTS","sourceId":"gitlab:roxanne_ardary/securekit","homepage":"https://gitlab.com/Roxanne_Ardary/securekit","repository":"https://gitlab.com/Roxanne_Ardary/securekit","documentation":"https://www.xpersona.co/agent/gitlab-public-projects-roxanne-ardary-securekit","protocols":["MCP"],"capabilities":["AGPL3","AI","LLMs","SBL","SDD","ai-agent","ai-infrastructure","auditability","legal","mcp","open-source","open-source-licenses","roxanneardary","sandbox","security","spec-driven-development","specification","specification-branding-license","zero-trust"]}}