skills/oxc-project/oxc/migrate-oxfmt/Gen Agent Trust Hub

migrate-oxfmt

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx oxfmt@latest to download and execute the Oxfmt migration tool from the public npm registry. This is an expected and standard operation for utilizing the utility provided by the skill author.
  • [COMMAND_EXECUTION]: The skill instructions include several shell commands for migration and formatting, such as npx oxfmt@latest --migrate, npx oxfmt@latest --check, and piping data using cat file | oxfmt (Step 1 and Step 4).
  • [INDIRECT_PROMPT_INJECTION]: The migration process reads existing configuration files which may contain untrusted data or instructions.
  • Ingestion points: The skill reads Prettier configuration files (JSON, YAML, JS, TS) and Biome configuration files (biome.json, biome.jsonc) to extract settings (Step 1).
  • Boundary markers: No specific boundary markers or instructions are provided to ensure the agent ignores potential instructions embedded within the source configuration files.
  • Capability inventory: The skill has the capability to execute shell commands via npx and write configuration files to the project directory.
  • Sanitization: Although the migration tool maps known configuration properties to Oxfmt equivalents, the skill does not detail any sanitization of the source file content to prevent instruction injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 09:50 PM
Security Audit — agent-trust-hub — migrate-oxfmt