The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides access to the calendly CLI tool for managing scheduling data. It includes operational rules that require the agent to verify connection status before execution and mandates user confirmation before performing any destructive actions or mutations via the request command.
[EXTERNAL_DOWNLOADS]: The skill connects to api.calendly.com and auth.calendly.com for API operations and OAuth authentication. These are official domains for the Calendly service and are consistent with the skill's primary purpose.
[INDIRECT_PROMPT_INJECTION]: As the skill ingests external data from calendar events and account details, there is an inherent risk of indirect prompt injection if that data contains malicious instructions designed to manipulate the agent.
Ingestion points: Event listings and user details retrieved via calendly list-events, calendly event-types, and calendly request in SKILL.md.
Boundary markers: Absent; there are no specific prompt delimiters or instructions to ignore embedded commands within the retrieved data.
Capability inventory: The skill has the ability to execute CLI commands and perform data mutations via the api.write action defined in manifest.yaml.
Sanitization: Absent; the provided files do not specify sanitization or filtering of the content retrieved from external API calls.

calendly