The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses npx --yes kenkeep@latest to download and run the kenkeep utility from the NPM registry. This occurs at runtime without a pinned version, which is a minor supply chain risk.
[COMMAND_EXECUTION]: Executes several shell commands, including node to run a local discovery script (.ai/kenkeep/scripts/kk-detect-root.mjs), npx for the core logic, and system utilities like uuidgen and date for logging and session management.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it reads and processes documentation files from the project repository which could contain malicious instructions.
Ingestion points: Markdown files discovered in the project repository via the finddocs primitive.
Boundary markers: Absent. The instructions do not wrap ingested content in specific delimiters or provide instructions to ignore embedded commands.
Capability inventory: Includes the ability to write files to disk via node write, rebuild indices, and delegate tasks to sub-agents.
Sanitization: No explicit content sanitization or validation of the documentation content is performed before processing.

kk-bootstrap