The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands including find for directory discovery and ln -s for symbolic link creation. The use of positional arguments ([skill names]) without explicit sanitization instructions presents a potential command injection surface if the input contains shell metacharacters.
[INDIRECT_PROMPT_INJECTION]: The skill performs a read operation on SKILL.md files after linking them. This facilitates the ingestion of external file content into the agent's context.
Ingestion points: The skill reads SKILL.md files from dynamically identified directories.
Boundary markers: There are no instructions to use delimiters or ignore instructions within the read files.
Capability inventory: The skill has the ability to traverse the filesystem, create links, and read file contents.
Sanitization: No content validation or sanitization is specified.

link-skills