vscode-project-init

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill uses a placeholder <project-name> in a shell command which is intended to be replaced by user input. This creates a surface for indirect prompt injection and command injection if the input contains shell metacharacters, as no sanitization or boundary markers are specified in the instructions.
  • [COMMAND_EXECUTION]: The agent is instructed to execute shell commands to scaffold the project and manage dependencies: npx --package yo --package generator-code -- yo code <project-name> --template typescript --quick and npm install.
  • [EXTERNAL_DOWNLOADS]: The skill fetches and executes initialization tools (yo, generator-code) from the npm registry at runtime via npx.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:05 PM
Security Audit — agent-trust-hub — vscode-project-init