The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the documents it processes.
Ingestion points: The skill reads content from .tex and .qmd files located in the Slides/ and Quarto/ directories as part of the proofreading process.
Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when passing file content to the proofreader agent.
Capability inventory: The skill utilizes the Agent and Task tools to process data and the Write tool to generate report files in the quality_reports/ directory.
Sanitization: The instructions do not specify any sanitization, escaping, or filtering of the external file content before it is processed by the AI sub-agent.

proofread