The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The script scripts/generate_image.py implements logic to read sensitive authentication keys from the standard Alibaba Cloud credentials file located at ~/.alibabacloud/credentials. It also includes functionality to load environment variables from .env files in the current working directory and the repository root.
[EXTERNAL_DOWNLOADS]: The skill requires the installation of the dashscope Python library via pip. Additionally, the scripts/generate_image.py script uses the urllib.request module to download generated image files from remote URLs provided by the DashScope API response.
[INDIRECT_PROMPT_INJECTION]: The skill accepts arbitrary text prompts for image generation, creating a surface for indirect prompt injection where instructions embedded in processed data could influence the agent's behavior.
Ingestion points: The prompt and negative_prompt fields in the image.generate request, processed in SKILL.md and scripts/generate_image.py.
Boundary markers: No delimiters or boundary markers are used to isolate user-provided prompts from the execution context.
Capability inventory: Network access via urllib.request and the DashScope API, and file system write access to the output/ directory (scripts/generate_image.py).
Sanitization: No sanitization or validation of the prompt content is performed before transmission to the API.
[COMMAND_EXECUTION]: The skill provides instructions for executing shell commands to install dependencies, validate scripts using py_compile, and run a Python helper script to perform image generation and download operations.

aliyun-qwen-image