The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes a local Dart script located at scripts/wrap_lines.dart to format Markdown text. This script performs file reading and writing operations on user-provided Markdown files.
[PROMPT_INJECTION]: The skill processes untrusted Markdown content, which presents an attack surface for indirect prompt injection. Ingestion points: Content of Markdown files targeted for proofreading. Boundary markers: Absent; there are no delimiters or specific instructions to ignore embedded instructions in the input files. Capability inventory: The skill has the ability to read and modify local files via the agent and the provided Dart script. Sanitization: No sanitization or filtering of the input Markdown content is performed before processing.

proofread-markdown