The Agent Skills Directory

[DATA_EXFILTRATION]: The skill reads WeChat API credentials (AppID and AppSecret) from a local aws.env file. These credentials are transmitted to official WeChat API endpoints (api.weixin.qq.com) to authenticate and perform publishing tasks. This behavior is documented and is essential for the skill's primary function as an automation tool.
[COMMAND_EXECUTION]: The skill executes local Python scripts (publish.py, getdraft.py, article_init.py) using python3 to manage article preparation and API interactions. These scripts are part of the skill's own package.
[EXTERNAL_DOWNLOADS]: The documentation references the installation of standard, well-known libraries (PyYAML, Pillow) from official package registries to support article processing.
[PROMPT_INJECTION]: The skill processes content from article files (article.html and article.yaml) which constitutes an attack surface for indirect prompt injection.
Ingestion points: Untrusted data enters the workflow from the article.html and article.yaml files within the article directory.
Boundary markers: There are no explicit boundary markers or instructions to ignore instructions embedded within the processed article content.
Capability inventory: The skill has the capability to perform network operations (API calls), write to files (updating status in article.yaml), and execute shell commands.
Sanitization: No explicit sanitization or filtering of the HTML or YAML content is performed before it is uploaded or processed by the scripts.

aws-wechat-article-publish