cursor-usage-analysis
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Cursor Enterprise API, including user-controlled fields like member names, emails, and organizational groups.
- Ingestion points: Data is ingested via tools from the
cursor-usageMCP server that query theapi.cursor.comservice. - Boundary markers: The instructions lack specific delimiting markers or guidelines for the agent to distinguish between raw usage data and potential instructions embedded within data fields.
- Capability inventory: The skill possesses analytical capabilities (spending, active users, model usage) and the documentation mentions a capability to set user spending limits via the Admin API.
- Sanitization: No explicit logic or instructions are provided for the validation or escaping of API-returned data before it is presented to the user or used in further decision-making.
- [EXTERNAL_DOWNLOADS]: The skill references an external dashboard repository on GitHub.
- Evidence: Reference to
https://github.com/ofershap/cursor-usage-trackerin theSKILL.mdfile. - Context: This is a resource provided by the skill author for historical data visualization and does not involve automated remote code execution.
Audit Metadata