The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from external sources, such as resumes and project descriptions, to populate story banks and practice questions.
Ingestion points: Data enters the skill context from user input and upstream skills like cv-resume-builder and portfolio-presentation, as noted in references/workflow-integration.md.
Boundary markers: The skill does not implement delimiters or safety instructions to distinguish between system instructions and user-provided data.
Capability inventory: The skill is instructional in nature and does not perform network operations, file writing, or system command execution.
Sanitization: There is no evidence of sanitization or filtering to prevent embedded instructions in user data from influencing the agent's behavior.

interview-preparation