The Agent Skills Directory

[SAFE]: The skill operates entirely within the scope of document processing. It uses standard file reading and writing operations to convert user input into meeting minutes based on a provided schema.
[DATA_INDIRECT_INJECTION]: The skill possesses a surface for indirect prompt injection as it processes untrusted content from user-uploaded files (.pdf, .docx, .txt, .md). However, the capabilities associated with this skill are limited to generating text and writing to a local output directory, which presents minimal risk.
Ingestion points: SKILL.md (Step 1) reads user-provided text and file paths.
Boundary markers: No explicit delimiters or instructions are used to ignore embedded commands in the source data.
Capability inventory: The skill uses tools for reading files, asking user questions, and writing markdown files to a specific subdirectory.
Sanitization: No specific sanitization or filtering logic is described for the input content.

meeting-minutes