The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest external data to populate its knowledge base.
Ingestion points: The agent is instructed to find high-quality resources and record them in RESOURCES.md, which are then used to generate lessons in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or boundary markers when processing external content.
Capability inventory: The skill utilizes Read, Write, and Edit tools and is encouraged to use CLI commands to open files.
Sanitization: No explicit sanitization or validation steps are defined for content retrieved from external URLs or communities.
[COMMAND_EXECUTION]: The instructions contain a directive to use the command line for file operations.
Evidence: The skill states: "If possible, open the lesson file for the user by running a CLI command." This creates a potential vector for command injection if the filename or the environment allows for arbitrary command execution.
[EXTERNAL_DOWNLOADS]: The skill metadata and body refer to an upstream source for its logic.
Evidence: The skill is imported from mattpocock/skills and mentions a validator script at .agent-skills/skill-standardization/scripts/validate_skill.sh.

teach