The Agent Skills Directory

[COMMAND_EXECUTION] (SAFE): The skill utilizes standard development commands (pnpm run dev, pnpm run build) within the local project directory. These commands are necessary for local development and build verification of the documentation site.
[DATA_EXPOSURE] (SAFE): The instructions direct the agent to read internal repository source files (cli.rs, rcfile.rs, etc.) to extract information for documentation. This is consistent with the stated purpose of the skill and does not involve accessing sensitive user credentials or system secrets.
[INDIRECT_PROMPT_INJECTION] (LOW): The skill possesses a surface for indirect prompt injection as it processes codebase source files to generate documentation.
Ingestion points: Local source files including src/cli.rs, src/rcfile.rs, and src/instance_state.rs.
Boundary markers: Absent; there are no specific delimiters defined for the source code ingestion.
Capability inventory: Read/write access to project files and local shell execution via pnpm.
Sanitization: Absent; the skill relies on the agent's logic to transform source code into documentation. The risk is considered low as the output is restricted to documentation files.

document-code