News
Secure Claude Enterprise with Cisco AI Defense - Cisco Blogs
Publication date not yet evaluated · Added cisco.com
Page published
Coverage timeline
Single-source analysis — one report is available.
Why it matters
Anthropic's inference hooks enabling third-party runtime inspection of prompts and MCP tool transcripts signal an emerging ecosystem model for defending agentic AI against prompt injection and tool-poisoning at runtime.
Cisco describes an integration between Cisco AI Defense and Claude Enterprise that uses Anthropic's newly introduced inference hooks to inspect each governed prompt before inference, returning an allow/deny verdict to block prompt injection and jailbreak attempts. The piece also notes evaluation of agent conversation transcripts, including MCP tool calls and results, to catch poisoned content before the next inference.