writing-proofreading
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
npx markdownlint-cli2command to validate and automatically fix formatting issues in Markdown files. - [EXTERNAL_DOWNLOADS]: The
markdownlint-cli2package is downloaded from the npm registry at runtime via thenpxutility. This is a standard and expected operation for this tool. - [PROMPT_INJECTION]: The skill processes user-controlled article content, presenting a surface for indirect prompt injection.
- Ingestion points: Content is read from
article.mdor other user-provided documents. - Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed file content.
- Capability inventory: The agent can execute shell commands via
npxand perform file read/write operations. - Sanitization: The skill does not perform any sanitization or validation of the input article content before processing.
Audit Metadata