The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided answers and reference source code to navigate a decision tree.
Ingestion points: Processes user responses through the ask_user_question tool and accepts user-provided source code as reference implementations.
Boundary markers: No specific delimiters or safety instructions are defined to separate user-provided content from the agent's core instructions.
Capability inventory: The skill allows the agent to read the local codebase to verify facts and clarify project requirements.
Sanitization: There are no explicit instructions for sanitizing or validating the reference code or user answers provided during the interview.

core-interview