The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-provided input from the $ARGUMENTS variable to generate documentation content, creating a vulnerability surface for indirect prompt injection.
Ingestion points: The documentation topic and substantive content are derived directly from the $ARGUMENTS provided by the user.
Boundary markers: The workflow lacks explicit delimiters or instructions to the agent to treat the user-supplied content as untrusted data or to ignore potentially malicious instructions embedded within that data.
Capability inventory: The skill utilizes the Write, Read, and Glob tools to create and manage markdown files within the .chalk/docs/ directory structure.
Sanitization: There is no evidence of sanitization, validation, or escaping of the user-provided input before it is written to the local filesystem.

create-doc