baoyu-format-markdown
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user data from markdown or plain text files to generate metadata such as titles and summaries. This represents an indirect prompt injection surface where content within the processed files could theoretically attempt to influence the agent's behavior or output. * Ingestion points: The workflow reads user-specified files in SKILL.md Step 1. * Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the processing logic. * Capability inventory: The skill has the capability to read and write files and execute shell commands via local scripts. * Sanitization: The skill does not perform explicit sanitization or filtering of the input file content prior to processing metadata fields.
- [COMMAND_EXECUTION]: The skill executes shell commands to invoke formatting scripts and external typography tools. Specifically, it runs a main TypeScript entry point via bun and utilizes npx to run the autocorrect-node utility for text spacing fixes.
- [EXTERNAL_DOWNLOADS]: The skill relies on external Node.js packages for markdown parsing and transformation, as defined in the package.json and bun.lock files. It also dynamically invokes the autocorrect-node package during execution.
Audit Metadata