The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and execute the @useclawlink/cli package from the public NPM registry. This package is the primary interface for the ClawLink service.
[COMMAND_EXECUTION]: The skill instructs the agent to run shell commands via npx to manage Coda authentication, list actions, and execute operations within Coda documents.
[CREDENTIALS_UNSAFE]: The skill documentation indicates that login credentials for the service are stored locally at ~/.clawlink/credentials.json. This is a sensitive file path containing authentication material.
[PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and process data from external Coda documents.
Ingestion points: Data is brought into the agent context via actions such as coda_get_a_column and coda_get_content_types (SKILL.md).
Boundary markers: None identified in the skill instructions to separate document content from agent instructions.
Capability inventory: The skill can perform write operations in the external service via npx @useclawlink/cli run coda (SKILL.md).
Sanitization: No specific sanitization or filtering of document content is described, although the skill advises the agent to confirm with the user before performing write actions.

coda