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-cli2 command to validate and automatically fix formatting issues in Markdown files.
  • [EXTERNAL_DOWNLOADS]: The markdownlint-cli2 package is downloaded from the npm registry at runtime via the npx utility. 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.md or 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 npx and perform file read/write operations.
  • Sanitization: The skill does not perform any sanitization or validation of the input article content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 7, 2026, 11:57 AM