The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external sources, including a feature development guide and user-provided notes files (e.g., @notes.md). This creates a surface where instructions embedded within those files could potentially influence the agent's output during the document generation phase.
Ingestion points: The skill instructions explicitly tell the agent to read @~/.local/share/dotfiles/ai/guides/feature-development-process.md and any files tagged by the user as @notes.md or similar.
Boundary markers: No specific delimiters or "ignore instructions" warnings are defined for the content ingested from these files.
Capability inventory: The skill instructs the agent to create new files on the filesystem (vision.md, future.md, and discussion-summary.md).
Sanitization: There are no instructions for sanitizing or filtering the content read from external files before using it to generate documentation.

feature-vision