The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes repository content to generate and synchronize documentation files, which theoretically presents an injection surface for instructions embedded in source files.
Ingestion points: The skill reads directory names via find and individual file contents to identify "invisible knowledge" and architectural prose across the repository.
Boundary markers: No explicit markers are used to delimit external repository content from the agent's internal instructions during processing.
Capability inventory: The skill has permissions to list directories, read file contents, and write/modify CLAUDE.md and README.md files.
Sanitization: There is no evidence of sanitization or escaping of the ingested file content before it is processed or written back to the filesystem.

doc-sync