The Agent Skills Directory

[Indirect Prompt Injection] (HIGH): The skill's core functionality involves processing and modifying external content files, which presents a vulnerability surface where instructions embedded in those files could influence or override the agent's behavior.
Ingestion points: The skill targets and reads data from files matching content/**/*cheat-sheet*.md.
Boundary markers: There are no specified delimiters or instructions used to isolate untrusted content from the agent's operational instructions.
Capability inventory: The skill is authorized to 'create' and 'edit' cheat sheet content, implying write access to the filesystem.
Sanitization: The instructions do not describe any validation or sanitization mechanisms for the data being processed or written.

cheat-sheets