# Claude Sonnet 5.5 adds cyber safeguards and may route higher-risk requests to Sonnet 5

DevFeed: [Claude Sonnet 5.5 adds cyber safeguards and may route higher-risk requests to Sonnet 5](<https://devfeed.tech/articles/you-picked-claude-sonnet-5-5-but-anthropic-may-send-your-request-to-sonnet-5-in-higher-risk-situations-61395.md>)

Original publisher: [Read original article](<https://thenewstack.io/claude-sonnet-cyber-safeguards/>)

Author: Amanda Caswell

Published: 2026-09-28T21:34:23Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [Claude](<https://devfeed.tech/topics/claude.md>), [AI software supply chain security](<https://devfeed.tech/topics/ai-software-supply-chain-security.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>), [Vulnerabilities](<https://devfeed.tech/topics/vulnerabilities.md>)

Tags: [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [anthropic](<https://devfeed.tech/tags/anthropic.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [claude-sonnet-5](<https://devfeed.tech/tags/claude-sonnet-5.md>), [claude-sonnet-5-5](<https://devfeed.tech/tags/claude-sonnet-5-5.md>), [cybersecurity](<https://devfeed.tech/tags/cybersecurity.md>), [exploit-development](<https://devfeed.tech/tags/exploit-development.md>), [security](<https://devfeed.tech/tags/security.md>), [terminal-bench-4-0](<https://devfeed.tech/tags/terminal-bench-4-0.md>)

## AI overview

Anthropic launched Claude Sonnet 5.5 with cyber safeguards and fallback routing that may send higher-risk requests to Sonnet 5. The model scores well on the cited coding benchmark and has improved substantially on offensive security tasks, prompting safeguards similar to those used for more capable models. Its protections may also lead to more refusals on legitimate cybersecurity work.

## Source excerpt

Anthropic's Claude Sonnet 5.5, released Monday, is the first Sonnet model to launch with cyber safeguards and model fallbacks like The post You picked Claude Sonnet 5.5 -- but Anthropic may send your request to Sonnet 5 in "higher-risk" situations appeared first on The New Stack.