The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local Python script (scripts/cache_docs.py) to manage documentation caching. The execution uses arguments (--permalink) derived from a mapping table within the skill instructions.
[EXTERNAL_DOWNLOADS]: The skill fetches documentation content from the vendor's official domain (jeesite.com). This is used to provide up-to-date technical support information to the user.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. It reads and processes Markdown files that are downloaded from an external source and stored in a local cache.
Ingestion points: Content is fetched from https://jeesite.com/docs/support/ and stored in references/.cache/support/ or ~/.cache/jeesite/support/ (SKILL.md).
Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the documentation reading phase.
Capability inventory: The agent can execute the cache_docs.py script and read/process multiple Markdown files (__00.md to __NN.md) from the cache directory (SKILL.md).
Sanitization: There is no evidence of content sanitization or validation before the agent processes the downloaded Markdown content.

support