The Agent Skills Directory

[PROMPT_INJECTION]: An indirect prompt injection surface is present due to the ingestion of untrusted local data into the agent's reasoning loop.
Ingestion points: The skill instructions direct the agent to read file content from .context/profile.md, .context/projects/_index.md, and project-specific context files.
Boundary markers: There are no explicit delimiters or specific 'ignore embedded instructions' warnings provided when processing these files.
Capability inventory: The skill is granted Read, Write, and Edit capabilities to interact with the filesystem.
Sanitization: The skill does not perform sanitization, escaping, or validation of the text retrieved from the context files before using it to drive the interview process.

interview-me