THREAT OPS › Threat News › Understanding Claude Tag’s access model in Slack and how to configure it securely
Understanding Claude Tag’s access model in Slack and how to configure it securely
<p>Anthropic’s new AI agent for Slack acts under an admin-configured access bundle rather than each user’s own credentials. Here’s how that model works, what admins should understand and how to securely configure it.</p><div class="blog-see-also"><div class="col-sm-12"><h2>Key takeaways</h2><ol><li>Claude Tag, Anthropic’s newly launched AI agent for Slack, acts on connected services using shared c
MITRE ATT&CK techniques
- CredentialsT1589.001
Indicators of compromise
- https://www.anthropic.com/news/introducing-claude-tagurl
- https://claude.com/docs/claude-tag/concepts/glossary#access-bundleurl
- https://claude.com/docs/claude-tag/admins/attach-to-scopeurl
- https://claude.com/blog/agent-identity-access-modelurl
Original source: https://www.tenable.com/blog/claude-tag-slack-access-model