calendly-automation
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and act upon data from external Calendly resources.
- Ingestion points: Data from external Calendly events, invitee profiles, and scheduling links are retrieved via tools defined in
SKILL.md. - Boundary markers: There are no defined delimiters or specific instructions to the agent to disregard natural language instructions found within the retrieved data.
- Capability inventory: The skill possesses high-impact capabilities including
CALENDLY_CANCEL_EVENTandCALENDLY_REMOVE_USER_FROM_ORGANIZATIONas specified inSKILL.md. - Sanitization: No sanitization or validation logic is present to filter malicious content from the retrieved data before it enters the agent's context.
- [EXTERNAL_DOWNLOADS]: The skill requires the configuration of an external MCP server endpoint at
https://rube.app/mcpto function. - [NO_CODE]: The skill consists entirely of markdown instructions and metadata, with no accompanying Python or JavaScript code files.
Audit Metadata