The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from existing project documentation and user-provided arguments to generate new files.
Ingestion points: The skill reads files from .chalk/docs/product/ and .chalk/docs/engineering/ and parses the $ARGUMENTS variable.
Boundary markers: There are no explicit instructions for the agent to treat this data as untrusted or to use delimiters to separate ingested content from system instructions.
Capability inventory: The skill utilizes the Write tool to create new markdown files based on the aggregated data.
Sanitization: The instructions do not include steps for sanitizing, escaping, or validating the external content before processing or writing it to the filesystem.

create-prd