The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using npx @useclawlink/cli. This is the primary mechanism for authentication, data retrieval, and performing actions in Calendly.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and run the @useclawlink/cli package from the NPM registry. This package is provided by the skill's vendor and is used to interface with their hosted service.
[CREDENTIALS_UNSAFE]: The skill documents that authentication tokens are stored locally at ~/.clawlink/credentials.json. While this is standard behavior for CLI tools, it establishes a location for sensitive access tokens on the user's filesystem.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources (Calendly events, invitees, and schedules). If these external records contain malicious instructions, they could potentially influence the agent's behavior.
Ingestion points: Calendly event details, invitee information, and availability schedules are read into the agent's context via the list and get actions defined in SKILL.md.
Boundary markers: None identified in the provided instructions to delimit external data from agent instructions.
Capability inventory: The agent has the capability to execute shell commands and write data back to Calendly using the CLI tool as described in SKILL.md.
Sanitization: No explicit sanitization or validation of the retrieved Calendly data is mentioned in the skill definition.

calendly