33 pages for safeguards.

Safeguards Claude Documentation · title claude-science/safeguards Or, for the model with the same capabilities and no access approval requirement: Claude Developer Platform · in the page about-claude/models/migration-guide …when and how to properly use its tools. 8. **Real-time cybersecurity safeguards:** Newly added in Claude Opus 4.7, requests that involve prohibited or high-risk topics may lead to refusals. For legit… optimizing-for-cost-and-intelligence Claude Developer Platform · in the page about-claude/models/optimizing-for-cost-and-intelligence …none of its attempts was cut short by the safety classifiers, under a safeguards deployment newer than the one the other models ran under. 8. **Corpus defect sweep:** Anthropic-internal, for work larg… enterprise Claude Developer Platform · in the page agents-and-tools/agent-skills/enterprise …data to an outside service, or instructions that tamper with Claude's safeguards. A Skill that fails the scan, or whose scan hasn't finished, is blocked from use. A Skill that passes with a warning st… memory-tool Claude Developer Platform · in the page agents-and-tools/tool-use/memory-tool …r application executes every file operation Claude requests, so these safeguards are your responsibility: ### Sensitive information Claude usually refuses to write sensitive information to memory fi… strict-tool-use Claude Developer Platform · in the page agents-and-tools/tool-use/strict-tool-use …ge content (prompts and responses), where it is protected under HIPAA safeguards. For ZDR and HIPAA eligibility across all features, see [API and data retention](https://platform.claude.com/docs/en/m… sent_count = len(messages sent in the compaction request) Claude Developer Platform · in the page build-with-claude/compaction …e model not to call tools. The summarization call runs under the same safeguards as any other request. ### When no summary comes back A summary is produced only when the summarization call ends norm… compaction-on-demand Claude Developer Platform · in the page build-with-claude/compaction-on-demand …e model not to call tools. The summarization call runs under the same safeguards as any other request. ## Handle a missing summary or an error A summary is produced only when the summarization call… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …curity work and beneficial life sciences tasks may also trigger these safeguards. To re-route declined requests automatically, configure [server-side or client-side fallback](https://platform.claude.c… refusals-and-fallback Claude Developer Platform · in the page build-with-claude/refusals-and-fallback …on:, model:, served_by_fallback:}) ``` </CodeGroup> Anthropic sets safeguards for each model individually and for each policy category, in line with the model's capability: depending on the categor… structured-outputs Claude Developer Platform · in the page build-with-claude/structured-outputs …ge content (prompts and responses), where it is protected under HIPAA safeguards. For ZDR and HIPAA eligibility across all features, see [API and data retention](https://platform.claude.com/docs/en/m… access-transparency Claude Developer Platform · in the page manage-claude/access-transparency …| The Anthropic team that performed the access (for example, `Safeguards`) | | `reason_code`… api-and-data-retention Claude Developer Platform · in the page manage-claude/api-and-data-retention …onsole. HIPAA readiness applies a broader set of privacy and security safeguards than ZDR (encryption, access controls, and audit logging that protect PHI throughout its lifecycle) rather than requiri… Opus migration Claude Developer Platform · in the page models/opus-5/migration-guide …when and how to properly use its tools. 8. **Real-time cybersecurity safeguards:** Newly added in Claude Opus 4.7, requests that involve prohibited or high-risk topics may lead to refusals. For legit… Sonnet migration Claude Developer Platform · in the page models/sonnet-5/migration-guide …lt value are not accepted and return a 400 error. 6. **Cybersecurity safeguards:** Claude Sonnet 5 is the first Sonnet-tier model with real-time cybersecurity safeguards. Requests that involve prohib… whats-new-sonnet-5 Claude Developer Platform · in the page models/sonnet-5/whats-new-sonnet-5 …rency Hub](https://www.anthropic.com/transparency). ## Cybersecurity safeguards Claude Sonnet 5 is the first Sonnet-tier model with real-time cybersecurity safeguards. Requests that involve prohibit… claude-opus-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5 …le is customized via the style feature. </product_information> <fable_safeguards_routing> It's possible that the user may have selected a different Anthropic model, "Claude Fable 5", but their query w… mitigate-jailbreaks Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks …ur prompts, validation, and filtering strategies. ## Advanced: Chain safeguards Combine strategies for robust protection. Here's an enterprise-grade example with tool use: <Accordion title="Example… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …and tools that require user interaction. The [cross-session messaging safeguards](/docs/en/permission-modes#skip-all-checks-with-bypasspermissions-mode) still apply. See [How permissions are evaluated… Configure permissions Claude Code CLI · in the page agent-sdk/permissions …rough to your `canUseTool` callback. * The [cross-session messaging safeguards](/docs/en/permission-modes#skip-all-checks-with-bypasspermissions-mode) still apply. </Warning> #### Plan mode (`plan`… Scan your codebase for vulnerabilities Claude Code CLI · in the page claude-security …n3` first on your `PATH`, then start a new session. **You may see a "safeguards flagged this message" notice when scanning on a Fable model.** The message names the model, for example "Fable 5.1's sa… Error reference Claude Code CLI · in the page errors …| | `<model>'s safeguards flagged this message`… Choose a permission mode Claude Code CLI · in the page permission-modes …r `PreToolUse` hook `"allow"` approves * The [cross-session messaging safeguards](#skip-all-checks-with-bypasspermissions-mode) * Reads outside the working directories while [`permissions.blockReadsOu… Configure permissions Claude Code CLI · in the page permissions …ted-paths) such as `.git` and `.claude`. The [cross-session messaging safeguards](/docs/en/permission-modes#skip-all-checks-with-bypasspermissions-mode) still apply. Only use this mode in isolated env… Security Claude Code CLI · in the page security # Security > Learn about Claude Code's security safeguards and best practices for safe usage. ## How we approach security ### Security foundation Your code's security is paramount. Claude Code is… Configure server-managed settings Claude Code CLI · in the page server-managed-settings …user access to Claude Code * [Security](/docs/en/security): security safeguards and best practices Claude Science changelog Claude Documentation · in the page claude-science/changelog …Program (beta), you can now [choose a use case](/docs/claude-science/safeguards#choose-a-use-case) for your sessions * Saved credentials now reach Claude's code only when it asks for them and you a… Glossary Claude Documentation · in the page claude-science/glossary …un jobs on, or dispatch jobs from. **[Use case](/docs/claude-science/safeguards#choose-a-use-case)**: a research purpose that Anthropic has approved for your organization under the Life Sciences Veri… How Claude Science works with your data Claude Documentation · in the page claude-science/how-claude-science-works-with-your-data …covers Claude Code sessions, not Claude Science), Enterprise Frontier Safeguards, coverage under Anthropic's Business Associate Agreement (keep protected health information out of Claude Science), and… Account Claude Documentation · in the page government/account/profile …ettings. **Primary Owner** is the same as Owner with a few additional safeguards: a primary owner cannot be removed by other owners, and each organization can have at most three of them.… Users Claude Documentation · in the page government/org-admin/users …ner can open the admin portal as soon as they refresh. The following safeguards apply and the dropdown will refuse the change if any of them would be violated. * You cannot change your own role. To… Legal and compliance Claude Documentation · in the page third-party/claude-desktop/legal …oundry, HIPAA readiness (Anthropic's arrangement of a signed BAA plus safeguards for processing PHI) is not available, as described under [What HIPAA readiness does not cover](https://platform.claude.… Overview Claude Documentation · in the page third-party/claude-desktop/overview …ider), and Anthropic's HIPAA readiness arrangement (a signed BAA plus safeguards for processing PHI through the Claude API) does not cover Microsoft Foundry. See [What HIPAA readiness does not cover](…