baoyu-format-markdown

Warn

Audited by Gen Agent Trust Hub on Mar 25, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands like test, echo, and mv for configuration management and file backups. It also uses child_process.execSync in a TypeScript script to run an external typography tool on a file path, which could be exploited if the path is not properly sanitized.- [EXTERNAL_DOWNLOADS]: The skill invokes npx to download and execute the autocorrect-node package at runtime. It also uses npx -y bun to run its internal scripts, which may trigger downloads of the Bun runtime.- [PROMPT_INJECTION]: The skill implements an indirect prompt injection surface by reading and processing the content of user-provided markdown or plain text files to generate metadata such as titles and summaries.
  • Ingestion points: Source markdown or plain text files read in Step 1.
  • Boundary markers: None identified in the analysis workflow.
  • Capability inventory: File system access (writeFileSync, mv), command execution (execSync), and network access via npx downloads.
  • Sanitization: No explicit sanitization of file content or paths is performed before analysis or execution.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 25, 2026, 03:07 PM