The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read and interpret project configuration files, creating a surface where malicious instructions could be embedded in monorepo data to target the agent.
Ingestion points: Project configuration and source files, including turbo.json, package.json, and .env files as defined in SKILL.md and references/configuration/tasks.md.
Boundary markers: The skill uses markdown code blocks and structured JSON examples for documentation, but lacks explicit instructions for the agent to ignore or sanitize instructions found within user-provided project data.
Capability inventory: The skill utilizes shell command execution through the turbo CLI, package management operations via npm, pnpm, yarn, and bun, and git-based filtering.
Sanitization: There is no evidence of sanitization or validation logic for the content of the files ingested at runtime.

turborepo