The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run pnpm ai-docgen. This involves executing a local script or package defined within the project's environment.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and act upon content from files such as ai-docs/src and LLMS.md, which represents an attack surface for indirect instructions.
Ingestion points: The agent reads source files in ai-docs/src and existing documentation in LLMS.md (SKILL.md).
Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the content of these files as data rather than instructions.
Capability inventory: The skill possesses the capability to execute shell commands (pnpm) and modify files within the repository.
Sanitization: No sanitization, filtering, or validation steps are described for the data ingested from the project files.

ai-docs