google_admin-automation
Warn
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSDATA_EXFILTRATIONNO_CODE
Full Analysis
- [EXTERNAL_DOWNLOADS] (MEDIUM): The skill requires the addition of an external MCP server via
https://rube.app/mcp. As this domain is not on the trusted provider list, it introduces a potential supply-chain risk where the MCP provider could theoretically intercept administrative actions or data.\n- [DATA_EXFILTRATION] (LOW): The skill performs operations on sensitive directory data including users, groups, and emails. While these are intended administrative tasks, the data flows through the third-partyrube.appservice, representing a potential exposure surface.\n- [Indirect Prompt Injection] (LOW): \n - Ingestion points: Processes user and group data via
GOOGLE_ADMIN_LIST_USERSandGOOGLE_ADMIN_LIST_GROUPS.\n - Boundary markers: Absent; the instructions do not specify delimiters for data returned from the API.\n
- Capability inventory: High-impact tools including
GOOGLE_ADMIN_CREATE_USER,GOOGLE_ADMIN_DELETE_USER, andGOOGLE_ADMIN_SUSPEND_USER.\n - Sanitization: None specified; the skill assumes the agent or the MCP server handles potentially malicious content within directory fields.
Audit Metadata