The Agent Skills Directory

[COMMAND_EXECUTION]: The skill directs the agent to execute shell commands such as mkdir -p and git mv to establish and modify directory structures. It also instructs the agent to run arbitrary validation or linting commands that may already exist within the repository.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by ingesting and acting upon user-provided plans for exercise scaffolding.
Ingestion points: The workflow relies on parsing a plan provided by the user to extract names and types (SKILL.md).
Boundary markers: There are no delimiters or instructions provided to ensure the agent ignores any malicious instructions that might be embedded within the plan data.
Capability inventory: The skill utilizes directory creation (mkdir), file moving (git mv), and file writing (readme.md) as specified in SKILL.md.
Sanitization: No sanitization, validation, or escaping is performed on the data extracted from the plan before it is used in shell commands or file content.

scaffold-exercises