3 sources filed · EN 3
Prerequisite: a malicious or hijacked browser extension with access to claude.ai, and the user signed in to both the web app and Claude Desktop.
18 to 71 percentshare of known Claude accounts that were personal accounts, across six Forever Security customer organisations
Scout agents picked 5,034 audit targets (about 2.8 million lines, roughly 7% of the kernel) for $3,426; analyst agents produced 2,308 candidate findings in 12 hours for $316,549.
2,308 / 1,724candidate kernel findings after deduplication / vulnerabilities dynamically reproduced (~74.7%)
Incidents spanned North America, South America and Asia Pacific and several cloud and model providers; the number of incidents is not given.
over $100,000fraudulent charges in a single day in individual incidents
1 source filed · EN 1
Edits to Wikimedia wikis believed to come from OpenAI agents, almost all test edits in sandbox areas not visible to general readers.
millionsautomated API requests and crawled pages attributed to OpenAI-operated agents
1 source filed · EN 1
It draws on RAND's 2024 model-weights work, which maps five security levels (SL1-SL5) to five threat-actor capacities (OC1 amateurs to OC5 top nation-states).
5security clusters: access and interfaces, development and supply chain, monitoring and response, personnel, physical