The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the pippit-tool-cli command through multiple subcommands (+submit-run, get-thread, +upload-file, list-thread-file, download-result) to interact with the backend creation service.
[EXTERNAL_DOWNLOADS]: The instructions direct users to install the @pippit-dev/cli package via npx. This is an external dependency provided by the vendor.
[CREDENTIALS_UNSAFE]: The skill requires the XYQ_ACCESS_KEY environment variable to be set for authentication. While standard for CLI tools, it involves the handling of sensitive API credentials.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill processes content from local document files (.doc, .docx, .txt) uploaded by the user and readable_text returned from remote API calls via get-thread.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when processing or displaying these external data sources.
Capability inventory: The skill has the capability to write to the local file system through the download-result command and execute network operations via the CLI tool.
Sanitization: There is no explicit mention of sanitizing or escaping the content retrieved from external files or the remote API before it is processed or presented to the user.

xyq-short-drama-skill