The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the Bash tool to perform file system operations, including directory creation with mkdir -p, file creation via echo, and renaming with git mv. It also runs pnpm ai-hero-cli internal lint to validate the created structure.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user requirements to generate names for exercises and sections which are then used in shell commands. This creates a vulnerability surface where a malicious user could provide input designed to execute arbitrary commands. 1. Ingestion points: Workflow step 1 (Parse requirements) in SKILL.md. 2. Boundary markers: None explicitly defined. 3. Capability inventory: Shell command execution via Bash tool for file and directory management. 4. Sanitization: The skill does not provide specific instructions for escaping or validating user-generated names.

scaffold-exercises