The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructs the agent to use npx to download and execute the @useclawlink/cli package from the NPM registry. This is the vendor's official command-line interface.
[COMMAND_EXECUTION]: The core functionality of the skill relies on executing shell commands to perform GitHub actions, including login, connect, and run operations via the ClawLink CLI.
[CREDENTIALS_UNSAFE]: The documentation specifies that the service stores authentication credentials in a JSON file at ~/.clawlink/credentials.json. While this is a standard configuration for the CLI, it explicitly identifies the path to sensitive authentication material.
[INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection through its data ingestion capabilities.
Ingestion points: Data retrieved from GitHub, such as issue descriptions, pull request comments, and repository files, is processed by the agent (SKILL.md).
Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the data fetched from GitHub.
Capability inventory: The agent has the capability to execute shell commands (npx), read local files, and perform write operations back to GitHub (SKILL.md).
Sanitization: There is no mention of sanitization or filtering of external content before it is interpolated into the agent's context.

github