The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill's 'Update' and 'Find' modes involve reading existing Markdown documents, which introduces a vulnerability surface where instructions embedded in those files could influence agent behavior.
Ingestion points: Files are read from the roadmap/, strategy/, and planning/ directories.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when interpolating external file content into the prompt context.
Capability inventory: The skill possesses the capability to search, read, and write Markdown files across multiple project directories.
Sanitization: There are no mechanisms described for validating or escaping the content retrieved from the file system before processing.

roadmap-theme