The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the @useclawlink/cli tool via shell commands to interact with the Google Photos API. These operations are within the expected scope of a tool-based integration and facilitate authenticated requests to a well-known service provider.
[EXTERNAL_DOWNLOADS]: The skill installs and executes the @useclawlink/cli package from the NPM registry. This is the official distribution method for the vendor's command-line interface and is standard for Node.js-based integrations.
[CREDENTIALS_UNSAFE]: The documentation mentions that authentication tokens are stored locally at ~/.clawlink/credentials.json. This is standard behavior for CLI tools utilizing local secret storage and does not involve the use of hardcoded credentials or unsafe secret handling within the skill itself.
[INDIRECT_PROMPT_INJECTION]: The skill processes external content from the Google Photos API, creating a potential surface for indirect prompt injection. However, the skill explicitly instructs the agent to 'read first; confirm with the user before any write,' which serves as a critical human-in-the-loop security control to mitigate automated execution of malicious instructions found in photo metadata or albums.

googlephotos