THREAT OPS › Threat News › Monitoring AI agent sessions: Leveraging embedding models to aid threat hunting and attack discovery workflows
Monitoring AI agent sessions: Leveraging embedding models to aid threat hunting and attack discovery workflows
<p>Query rules find behavior you can define, but agent sessions contain unstructured behaviors you can only describe. I stored six months of my own Claude Code and Cursor sessions as semantic vectors in Elastic and searched them instead of handing every session to a large language model (LLM). One in seven sessions came back requiring triage of suspicious actions. We can then create rules to detec
MITRE ATT&CK techniques
- Unsecured CredentialsT1552
- CredentialsT1589.001
- Container APIT1552.007
- Unsecured CredentialsAML.T0055
- System PromptAML.T0069.002
Indicators of compromise
- https://arxiv.org/abs/2605.17380url
- https://staging.internal.example/healthurl
- static-www.elastic.codomain