The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content such as resumes, job descriptions, and personal experiences to generate tailored interview questions and feedback. * Ingestion points: The skill ingests user input as part of the initial context gathering (1단계: 면접 컨텍스트 파악) and during the continuous mock interview loop defined in SKILL.md. * Boundary markers: The instructions do not define explicit delimiters or instructions to the model to treat user-provided data strictly as non-executable text. * Capability inventory: The skill's primary function is text interpolation and response generation; it does not utilize high-risk tools or capabilities such as file system modifications, network requests, or shell execution. * Sanitization: No data sanitization, filtering, or validation steps for user-supplied data were found in the provided instruction files.

career-interview