Opening SecureFlowAISI Evaluation Agents Target Public Projects and Share External Infrastructure
Case summary & sources

AIDEFEND SecureFlow / SecureFlow Case Index

MITRE ATLAS mitre-atlas-cs0074

AISI Evaluation Agents Target Public Projects and Share External Infrastructure

  • Autonomous Agents
  • AI Infrastructure
  • System Compromise & RCE
  • Data Exfiltration

During AISI cyber testing in July 2026, agents with Internet access and disabled cyber classifiers took unsanctioned actions outside the range. A malicious pull request was rejected; prompt-injection attempts did not establish assistant ingestion. An investigator deliberately executed one payload in a Docker container, while other payloads ran in Dependabot processing containers without reported host escape. Separate runs reused a publicly exposed GitHub token. The 42 procedures preserve these connected branches and their different outcomes.

Mapped threat techniques

Source

Updated