The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using npx @useclawlink/cli to manage the lifecycle of the Productboard integration, including authentication, action discovery, and data modification.
[REMOTE_CODE_EXECUTION]: Runtime execution of remote code is performed via npx, which fetches and runs the @useclawlink/cli package from the NPM registry. This package is an official resource provided by the author, clawlink-hq.
[EXTERNAL_DOWNLOADS]: The skill retrieves the ClawLink CLI tool from the public NPM registry at runtime during the setup and usage phases.
[PROMPT_INJECTION]: The skill creates an attack surface for indirect prompt injection by ingesting data from the Productboard platform that could contain malicious instructions.
Ingestion points: Data returned from Productboard via the actions and run commands of the ClawLink CLI.
Boundary markers: No delimiters or isolation instructions are present in the provided command sequences to distinguish external data from agent instructions.
Capability inventory: The skill environment allows for subprocess execution (npx) and file system access.
Sanitization: The skill does not mention explicit sanitization or validation of the data retrieved from the external API before it is processed by the agent.

productboard