The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands such as curl, tar, and npm to manage environment configuration and install necessary tooling.
[EXTERNAL_DOWNLOADS]: Fetches Node.js binaries and verification checksums from the official nodejs.org distribution service. It also installs the @iqinghu/qhkit package from the npm registry.
[DYNAMIC_EXECUTION]: The skill instructs the agent to generate and execute inline scripts at runtime to handle image resizing tasks. This includes using python -c for processing with the Pillow library and npx to run the sharp-cli utility.
[INDIRECT_PROMPT_INJECTION]: The skill accepts user-provided prompts and images which are then passed to external CLI tools for processing.
Ingestion points: User-supplied prompt and uploadedImages fields as described in SKILL.md.
Boundary markers: None explicitly defined for user prompts; data is encapsulated in JSON objects passed to CLI commands.
Capability inventory: Includes shell command execution, file system interaction (reading/writing images), and network operations via the qhkit tool.
Sanitization: No specific input sanitization or validation logic is provided for user-generated content.
[CREDENTIALS_UNSAFE]: The instructions guide the agent to request an API token from the user and configure it using the qhkit config set --token command.

linkpix-kling-3-sales