calendly-automation
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection attacks as it ingests and processes external data from Calendly that could contain malicious instructions.
- Ingestion points: Untrusted data enters the agent context through tools like
CALENDLY_LIST_EVENTS,CALENDLY_LIST_EVENT_INVITEES, andCALENDLY_LIST_ORGANIZATION_INVITATIONS(SKILL.md). - Boundary markers: Absent; the instructions do not specify any delimiters or safety warnings to treat the retrieved content as data rather than instructions.
- Capability inventory: The skill includes high-impact capabilities such as
CALENDLY_CANCEL_EVENT,CALENDLY_REMOVE_USER_FROM_ORGANIZATION, andCALENDLY_CREATE_ORGANIZATION_INVITATION(SKILL.md). - Sanitization: Absent; there is no evidence of content escaping, validation, or filtering of the API responses.
- [EXTERNAL_DOWNLOADS]: The setup instructions require configuring an external service endpoint at
https://rube.app/mcpas an MCP server to provide the Calendly toolset (SKILL.md).
Audit Metadata