Safety #AI agents#Google Nov 13, 2026 · Originally published Nov 12

Google tests Agent Anomaly Detection on five outside benchmarks: it flags 87% of harmful instructions the agent carried out, but catches only 4 of 18 driven by poisoned long-term memory

Google ran its agent anomaly detector on public benchmarks it did not write, and reported the strengths, the false-alarm rates and a clear gap.

Image: Google Developers Blog
Primary source Google Developers Blog · developers.googleblog.com Read the original ↗

// Key points

  • The test used five public benchmarks, AgentDojo, InjecAgent, Agent Security Bench, AgentDyn and AgentHarm, 1,774 sessions in all, with an ADK agent on gemini-2.5-flash and each benchmark's deterministic check labeling the outcome.
  • Of harmful instructions the agent read and carried out, 87% were flagged: 85% on AgentDojo, 87% on InjecAgent, 99% on AgentDyn and 81% on AgentHarm.
  • False alarms ran 2% to 4% on benign office sessions and 16% on AgentHarm, whose benign tasks also post to social media, run terminal commands and download files.
  • The clear gap is memory poisoning: when instructions planted in long-term memory made the agent act, it caught 4 of 18.

Builder's takeA vendor testing on someone else's benchmarks and publishing the weak spots is worth copying. For product teams the takeaway is that after-the-fact detection catches most injections but long-term memory is a blind spot: agents like PandaClaws that remember user preferences need a separate check before anything is written to memory, with a traceable source for each write.

// Background · from #AI agents

Full timeline →
  1. Nov 13 Anthropic launches self-hosted Claude Managed Agents: the service, agents, sessions and history live on your own infrastructure, with model calls routable to Bedrock, Google Cloud or Foundry
  2. Nov 13 The next-generation AgentCore runtime becomes the default: sessions on a 2 GB image start in under 2 seconds at P75, down from 29.7, with up to 68% less billed memory for multi-turn agents
  3. Nov 12 Google launches the Gemini Decisions API: Gemini Decision 1 answers up to 1,000 closed-set questions in one pass at $0.10 per million input tokens, with no output billed

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →