Skills
skills/huynhsang2005/blog-tanstack/frontend-code-review/Gen Agent Trust Hub

frontend-code-review

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [Command Execution] (LOW): The skill instructs the agent to execute shell commands such as bun run build and bun run lint. While standard for a development workflow, these represent local execution capabilities.
  • [Indirect Prompt Injection] (LOW): The skill processes external .tsx and .ts files which creates a surface for indirect instructions. Ingestion points: Code files referenced in the review instructions. Boundary markers: None provided in the prompt instructions to distinguish code from instructions. Capability inventory: Local command execution via bun (SKILL.md). Sanitization: None specified for external file content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:38 PM