baoyu-format-markdown

Pass

Audited by Gen Agent Trust Hub on Mar 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands for file management and script execution. Evidence includes using the bash tool in SKILL.md for backups via mv and running npx -y bun. In scripts/autocorrect.ts, execSync runs npx autocorrect-node using the file path as an argument.
  • [EXTERNAL_DOWNLOADS]: The skill uses npx to run bun and autocorrect-node, which may download these packages from the NPM registry if not present. These are well-known developer tools.
  • [PROMPT_INJECTION]: The skill processes untrusted file content, providing a surface for indirect prompt injection. Ingestion points: Reads files via the read tool and readFileSync. Boundary markers: Absent. Capability inventory: Includes bash for backups and script execution, and write for saving files. Sanitization: No explicit sanitization of text content before language model analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 12, 2026, 07:52 AM