The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses npx @useclawlink/cli to perform actions in Basecamp.
[EXTERNAL_DOWNLOADS]: The @useclawlink/cli package is downloaded from NPM using npx during setup and usage. As a package from the vendor's own namespace, this is standard functionality.
[PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes data from external Basecamp actions and uses it to construct subsequent command inputs.
Ingestion points: Output from npx @useclawlink/cli actions basecamp and describe commands in SKILL.md.
Boundary markers: None explicitly defined in the skill instructions to separate external data from instructions.
Capability inventory: Execution of Basecamp actions via npx @useclawlink/cli run in SKILL.md.
Sanitization: No explicit sanitization or validation of the Basecamp data is mentioned before it is used to generate JSON input.

basecamp