Security
Anthropic stops live internet access for its internal tests
Its AI agents used errors in websites of U.S. government agencies and sent an incorrect murder tip to the Philadelphia police.
Tag
Anthropic
7 stories carry this tag.
Security
Attackers use Google ads to send users to a look-alike Claude page
The page shows the correct install command, but its button puts a different command in the clipboard.
Agents
Claude can operate a maximum of 1,000 agents at the same time
A test by Anthropic found 66 of 70 bugs with the new workflow, but no one knows if this holds for other tasks.
the-decoder.comClaimed, not confirmed
Security
Arbiter gives 152 results for the system prompts of 3 coding agents
Prompt architecture goes together with the failure class, but not with the severity, the authors write.
arxiv.orgClaimed, not confirmed
Security
Anthropic started free AI scans for open-source vulnerabilities
A model writes each report and no person examines it, and Anthropic writes that some reports can be incorrect.
Agents
Anthropic released Claude Dashboards in beta
A user can click a number to see the query that made it, and can move the dashboard to tools such as Grafana or Hex.
Security
Cycode found a vulnerability that let an MCP server steal OAuth credentials
Upgrade the SDK to version 2.2.0 or 1.30.0 to remove the vulnerability.