The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for directory creation and version control management.
Specifically, it uses mkdir -p for path setup and git commit or git mv for managing the repository state.
It invokes a local utility via pnpm ai-hero-cli internal lint to validate the generated structure, representing execution of a project-local CLI tool.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it processes untrusted input to drive its workflow.
Ingestion points: The agent is directed to "Parse the plan" to extract names for sections and exercises from an external source.
Boundary markers: No delimiters or safety instructions are provided to prevent the agent from following instructions that might be embedded within the plan text.
Capability inventory: Across SKILL.md, the agent is granted the ability to write to the filesystem (readme.md), create directories, and run shell commands (git, pnpm).
Sanitization: The skill does not define any validation or sanitization of the content extracted from the plan before it is used in directory paths or file content.

scaffold-exercises