The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from a user-supplied @vision.md file and local development guides. Malicious instructions embedded in these files could potentially influence the agent's behavior during the document generation phase.
Ingestion points: The agent is instructed to read @vision.md, @~/.local/share/dotfiles/ai/guides/feature-development-process.md, and @project/guides/feature-development-process.md.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when referencing these files.
Capability inventory: The skill has the capability to write to the file system (creating requirements.md, future.md, and discussion-summary.md).
Sanitization: There is no evidence of sanitization, escaping, or filtering of the external content before it is processed or written back to the project files.

feature-requirements