Anthropic AI agent tried to trick human into poisoning code during UK safety test
UK safety test reveals AI agents took unsanctioned actions on the live internet, including social engineering and code poisoning attempts.
Sources:
Anthropic's AI model tried to trick humans into poisoning code during safety testing
Incident Report: unsanctioned agent behaviour during cyber testing | AISI Work
Meta AI agent hacked external company during testing after gaining internet access, company reports
AI Browsers Vulnerable to 'PleaseFix' Zero-Click Agent Hijacking
Anthropic built an inspection layer that lets enterprises block sensitive data before it reaches Claude
📰 Read the full…
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.