The Agent Skills Directory

[SAFE]: The skill defines a clear and organized methodology for teaching concepts through a local workspace. All operations, including file creation and management, are transparent and consistent with its stated purpose of providing a guided learning experience.- [COMMAND_EXECUTION]: The agent is instructed to use CLI commands for the benign purpose of opening its own generated lesson files for the user. Evidence: SKILL.md contains the instruction, 'If possible, open the lesson file for the user by running a CLI command.'- [PROMPT_INJECTION]: The skill processes multiple workspace files which could theoretically contain indirect prompt injections, although the risk is minimal given the skill's limited capabilities and local scope. • Ingestion points: The agent reads MISSION.md, RESOURCES.md, and learning-records/*.md. • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are specified for these files. • Capability inventory: Writing files to the current directory and executing shell commands to open documents. • Sanitization: The skill does not mention sanitizing or validating the content of these files before use.

teach