Answer: Claude Code includes a permissions system, critical-path removals, web search summarization, and sandbox mode as built-in security features. Status: Confirmed Entry: tool/claude-code/permissions-and-security/built-in-security-features Revision: 1 Digest: sha256:d9f2929ceaba109e (changes whenever the content changes) Timeline: Created: 2026-11-13T03:02:56Z Last changed: 2026-11-13T03:02:56Z Last verified: 2026-11-20T12:17:10Z Next check: 2026-11-21T12:17:10Z Check interval: Daily Expected change: No fixed schedule Data: Field | Value | Source | As of permissions system | Permissions system | [1] | 2026-11-20 critical-path removals | Critical-path removals | [1] | 2026-11-20 web search summarization | Web search summarization | [1] | 2026-11-20 sandbox mode | Sandbox mode | [1] | 2026-11-20 Sources: [1] Anthropic. "Securely deploying AI agents". https://code.claude.com/docs/en/agent-sdk/secure-deployment.md Role: primary. Accessed: 2026-11-20T12:17:10Z Quote: "**Permissions system**: Permission rules decide whether a tool call runs, is blocked, or asks for approval first." (Supports: permissions system) Quote: "**Critical-path removals**: With the permission mode set to `default`, an `rm` or `rmdir` command recognized as removing your working directory or another" (Supports: critical-path removals) Quote: "**Web search summarization**: Search results are summarized rather than passing raw content directly into the context, reducing the risk of prompt injection from malicious web content." (Supports: web search summarization) Quote: "**Sandbox mode**: Bash commands can run in a sandboxed environment that restricts filesystem and network access." (Supports: sandbox mode) Published: 2026-11-20T02:56:32Z Snapshot SHA-256: 1d1ad468499aa0fe108ba85c10f0be7697958d9287cb77d67d439f2ca880fa02 (captured 2026-11-17T12:21:16Z) Verification: Method: Automated extraction from [1] with deepseek-flash (JSON output, thinking disabled). Every value was checked by code to appear verbatim in a quoted passage of [1]. On this check the text of [1] was unchanged since 2026-11-17T12:21:20Z, so the values verified then were kept. Cross-check: not-available at 2026-11-20T12:17:10Z. No independent second source is configured for this entry Last successful check: 2026-11-20T12:17:10Z Last attempt: 2026-11-20T12:17:10Z Notes and limitations: Extracted automatically from a single official source (section "Built-in security features"). Related: https://latestn.com/tool/claude-code/permissions-and-security/change-permission-mode How do I change the permission mode for a Claude Code SDK agent? https://latestn.com/tool/claude-code/permissions-and-security/change-permission-mode-2 How do I change the permission mode in Claude Code? https://latestn.com/tool/claude-code/permissions-and-security/choose-sandbox-for-threat-model How do I choose the right sandbox environment for my threat model in Claude Code? https://latestn.com/tool/claude-code/permissions-and-security/block-on-hook-failure How do I block a tool call in Claude Code when a hook callback fails? https://latestn.com/tool/claude-code/permissions-and-security/block-protected-file-edits How do I block Claude Code from editing protected files with a hook? https://latestn.com/tool/claude-code/permissions-and-security/block-reads-generated-vendored-code How do I block reads of generated and vendored code in Claude Code? https://latestn.com/tool/ All entries in AI tools Change log: Time | Event | Change | Source 2026-11-13T03:02:56Z | added | Entry created | — Changes for this entry as a feed: https://latestn.com/tool/claude-code/permissions-and-security/built-in-security-features/latest Challenge this entry: Open challenges: None How: If a value here is wrong or out of date, send what is wrong and a link to evidence. Challenges are queued and checked against the evidence; they do not change the entry by themselves. If the entry changes as a result, the change log says so. Form: https://latestn.com/dispute/tool/claude-code/permissions-and-security/built-in-security-features POST: https://latestn.com/dispute/tool/claude-code/permissions-and-security/built-in-security-features with claim, evidence_url, and optionally field and contact (form-encoded or JSON) GET: https://latestn.com/dispute/tool/claude-code/permissions-and-security/built-in-security-features?claim={what is wrong}&evidence_url={link} How to cite: LatestN. (2026). What built-in security features does Claude Code have? Revision 1, last verified 2026-11-20T12:17:10Z. https://latestn.com/tool/claude-code/permissions-and-security/built-in-security-features (accessed 2026-11-21T09:58:06Z). @misc{LatestN_tool_claude_code_permissions_and_security_built_in_security_features_r1, title = {What built-in security features does Claude Code have?}, author = {{LatestN}}, year = {2026}, howpublished = {\url{https://latestn.com/tool/claude-code/permissions-and-security/built-in-security-features}}, note = {Revision 1; digest sha256:d9f2929ceaba109e; last verified 2026-11-20T12:17:10Z; accessed 2026-11-21T09:58:06Z} } Reuse: License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) Attribution: Copying and adapting are allowed, including commercially, if you credit LatestN and link to the entry you used. Each entry ends with a ready-made citation. URL: https://latestn.com/tool/claude-code/permissions-and-security/built-in-security-features