{"data":{"id":"424f3843-facd-478c-83b3-d046264fcff9","title":"Build vs buy for AI coding agent security: own the plumbing, buy the coherent picture","summary":"The article argues that most teams aim their in-house AI security effort at a gateway or proxy, while coding agent incidents occur in the harness, settings and credentials within reach. It recommends owning model routing, spend, identity, credentials, CI rules and the audit pipeline, and buying detection and a plane that links gateway, endpoint and vendor records.","solution":"Own model routing, spend, identity, credentials, CI rules and the audit pipeline; configure every vendor's admin controls; buy detection and a plane that links gateway, endpoint and vendor records into one picture of every agent session across vendors and models.","labels":["security","industry"],"sourceUrl":"https://adversa.ai/blog/ai-coding-agent-security-build-vs-buy/","publishedAt":"2026-11-22T15:06:00.000Z","cveId":null,"cweIds":null,"cvssScore":null,"cvssSeverity":null,"severity":"info","attackType":[],"issueType":"news","affectedPackages":null,"affectedPackageNames":null,"affectedPackageRefs":null,"affectedVendors":["Anthropic","OpenAI"],"affectedVendorsRaw":["Claude Code","Codex","Cursor","GitHub Copilot","LiteLLM","Replit agent","Cloudflare AI gateway","Shopify","Spotify","Uber"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":null,"epssScore":null,"epssCheckedAt":null,"kevDateAdded":null,"advisoryAliases":null,"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":null,"disclosureDate":"2026-11-22T15:06:00.000Z","fixReleasedAt":null,"daysToFix":null,"fixCheckedAt":null,"capecIds":null,"crossRefCount":0,"attackSophistication":"moderate","impactType":["integrity","availability","confidentiality"],"aiComponentTargeted":"agent","llmSpecific":true,"classifierConfidence":0.85,"researchCategory":null,"atlasIds":null}}