The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or unauthorized data access were detected. The skill's operations are confined to legitimate Calendly API workflows as described in the documentation.
[NO_CODE]: This skill is entirely instructional and does not package any executable code, scripts, or binary files. It leverages existing MCP tools provided by the Rube ecosystem.
[EXTERNAL_DOWNLOADS]: The skill references the Rube MCP server endpoint (https://rube.app/mcp) for tool integration. This is a standard configuration requirement for the specified toolkit and does not involve downloading untrusted scripts.
[PROMPT_INJECTION]: The skill processes external data from Calendly (event details, invitee names, and messages), creating a potential surface for indirect prompt injection. This is inherent to the skill's purpose of managing external scheduling data.
Ingestion points: Event and invitee data retrieved via tools like CALENDLY_LIST_EVENTS and CALENDLY_LIST_EVENT_INVITEES mentioned in SKILL.md.
Boundary markers: No specific delimiters or instructions to ignore instructions within retrieved data are defined in the markdown.
Capability inventory: The skill includes write-capable tools such as CALENDLY_CANCEL_EVENT and CALENDLY_CREATE_ORGANIZATION_INVITATION.
Sanitization: No explicit sanitization or validation of retrieved Calendly data is performed within these high-level instructions.

calendly-automation