baoyu-format-markdown

Pass

Audited by Gen Agent Trust Hub on Jun 26, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a local TypeScript entry point (scripts/main.ts) to manage the formatting workflow. It also invokes the autocorrect-node utility via a system subprocess (spawnSync) to apply typography rules to the document. These are intended behaviors for the skill's formatting purpose.
  • [EXTERNAL_DOWNLOADS]: The skill uses the bun runtime and references the autocorrect-node package. These are standard tools typically fetched from the official npm registry during execution or setup.
  • [PROMPT_INJECTION]: The skill processes user-provided markdown or plain text files to perform content analysis and formatting. This ingestion of untrusted data creates a potential surface for indirect prompt injection.
  • Ingestion points: User-specified files are read and analyzed in Steps 1 and 2 of the workflow.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the processed files.
  • Capability inventory: The skill performs file system writes (writeFileSync in scripts/main.ts) and executes system commands (spawnSync in scripts/autocorrect.ts).
  • Sanitization: No explicit sanitization or filtering of the input file content is performed prior to analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 26, 2026, 08:18 AM
Security Audit — agent-trust-hub — baoyu-format-markdown