md-writer
Pass
Audited by Gen Agent Trust Hub on Apr 8, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use the
grepcommand to search for relevant markdown files (**/*.md) within the project. This is a standard and expected operation for the purpose of maintaining document cross-references. - [DATA_EXPOSURE]: The skill requires reading the frontmatter of local markdown files to establish bidirectional links. This file access is restricted to markdown content for the legitimate purpose of documentation management.
- [PROMPT_INJECTION]: The skill processes user-provided topics or filenames via the
$ARGUMENTSvariable and reads data from existing markdown files. While these represent potential surfaces for indirect injection, the skill's capabilities are focused on formatting and structuring documentation, posing a minimal risk in the context of its intended use.
Audit Metadata