The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted user-provided materials (PDFs and notes), which creates a potential surface for indirect prompt injection attacks. * Ingestion points: Student study materials, PDFs, and syllabus topics provided during interaction as defined in SKILL.md. * Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the prompt. * Capability inventory: The skill has no enabled tools, shell command access, or network operations. * Sanitization: There is no defined process for sanitizing or validating the content of the ingested materials.
[NO_CODE]: The skill consists entirely of natural language instructions and YAML metadata without any accompanying scripts, binary executables, or external software dependencies.

exam-ready