-
Detects a single authenticated user generating an unusually high number of denied Claude chat access attempts in a 24-hour window. That pattern fits automated chat enumeration or attempts to reach conversations outside the actor's permissions. Unauthenticated shared-link actors lack user.id and are excluded.
Read More -
Detects an unusually high number of Claude chat creation events for the same user email within a 24-hour period. Burst chat creation can indicate automated LLM abuse, resource hijacking to burn organizational quotas, or scripted workflows used to stage many parallel conversations for data processing or prompt-injection campaigns.
Read More -
Detects an unusually high number of Claude chat deletion events for the same user email within a single calendar day. Mass chat deletion can indicate an attempt to remove conversation history, cover tracks after misuse of Claude, or automated cleanup following data staging or prompt abuse.
Read More -
Detects an unusually high number of successful Claude chat snapshot creation events for the same user email within a rolling 24-hour window. Chat snapshots package conversation content into shareable exports; sustained creation volume can indicate staging of organizational chat data for exfiltration via Anthropic's web service or automated bulk export of sensitive prompts and responses.
Read More -
Detects an unusually high volume of Claude file uploads from the same user email and source IP within a rolling 24-hour period. Sustained upload activity can indicate staging of sensitive documents in Claude chats for later retrieval, automated ingestion of data into LLM workflows, or abuse of organizational Claude access to move files into the cloud service.
Read More -
Detects the first successful creation of a Model Context Protocol (MCP) server integration name in an Anthropic organization within the rule history window. MCP servers add external data pathways into Claude and can expose organizational data to third-party infrastructure. This is a New Terms rule keyed on
organization.idandanthropic.audit.mcp_server_nameso the same connector name can still alert in another tenant, while routine re-creation of an already-seen name in the same organization does not.
Read More -
Detects at least five failed Anthropic authentication events for the same user email within one hour. Failures are matched by authentication category and failure outcome (for example magic-link or SSO login failures). That pattern fits repeated guessing, stale magic link abuse, or automated login attempts against one account.
Read More -
Detects a single user performing at least two distinct organization discovery actions within a 10-minute window: listing users, exporting members, or viewing groups. Chaining these read actions maps membership and group structure and commonly precedes targeted role grants, invites, or data collection against high-value accounts.
Read More -
Detects when a Claude project owner or editor role is granted through a
role_assignment_grantedevent. Project owners and editors can access project chats, artifacts, and knowledge bases that may hold sensitive data. An attacker with organization access can grant these roles to persist access to high-value project content without holding organization admin privileges.
Read More -
This rule detects when a member is granted the organization owner role of a GitHub organization. This role provides admin level privileges. Any new owner role should be investigated to determine its validity. Unauthorized owner roles could indicate compromise within your organization and provide unlimited access to data and settings.
Read More -
This rule detects when a GitHub repository is deleted within your organization. Repositories are a critical component used within an organization to manage work, collaborate with others and release products to the public. Any delete action against a repository should be investigated to determine it's validity. Unauthorized deletion of organization repositories could cause irreversible loss of intellectual property and indicate compromise within your organization.
Read More -
This rule is part of the "GitHub UEBA - Unusual Activity from Account Pack", and leverages alert data to determine when multiple alerts are executed by the same user in a timespan of one hour. Analysts can use this to prioritize triage and response, as these alerts are a higher indicator of compromised user accounts or PATs.
Read More -
Detects a high number of unique private repo clone events originating from a single personal access token within a short time period.
Read More -
Detects when a new member is added to a GitHub organization as an owner. This role provides admin level privileges. Any new owner roles should be investigated to determine it's validity. Unauthorized owner roles could indicate compromise within your organization and provide unlimited access to data and settings.
Read More