The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use the open (macOS) and xdg-open (Linux) shell commands to automatically display generated HTML lessons to the user, creating a path for automated interaction with skill-generated artifacts.
[EXTERNAL_DOWNLOADS]: The skill utilizes web search tools to gather educational resources from external internet sources, presenting a routine reliance on external data ingestion.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes untrusted search results and incorporates them into workspace files and shell operations. Ingestion points: Untrusted data enters the agent context through the use of web search and MCP research tools specified in SKILL.md. Boundary markers: The instructions do not define delimiters or explicit 'ignore' markers to separate untrusted search data from the agent's primary instructions. Capability inventory: The skill has the capability to write files to the local workspace and execute shell commands (open, xdg-open) via the agent. Sanitization: There is no mention of sanitization, HTML escaping, or validation of the content retrieved from external sources before it is written into the lessons.

teach