skills/microsoft/vscode/code-review/Gen Agent Trust Hub

code-review

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • Code Review Workflow: The skill uses standard version control commands such as git status and git diff to identify and analyze local file changes, which is appropriate for its intended purpose.
  • Controlled Output: The skill's primary action is using the addComment tool to provide feedback. It explicitly instructs the agent not to modify files, perform commits, or execute other write operations, maintaining a safe operating scope.
  • Processing Untrusted Content: As the skill reads and reviews external code, it inherently processes content that could contain indirect prompt injections (e.g., instructions hidden in code comments). However, the instructions provide a clear framework for review criteria which helps maintain the agent's focus on technical analysis.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 07:11 AM
Security Audit — agent-trust-hub — code-review