integrating-vscode

Pass

Audited by Gen Agent Trust Hub on Apr 4, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: Includes standard VS Code CLI commands for managing extensions and workspaces (e.g., code --install-extension).
  • [DATA_EXFILTRATION]: Documents the use of the VS Code FileSystem API for reading workspace files, which is normal functionality for IDE extensions.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface where extensions built using these examples may process untrusted editor content. Ingestion points: vscode.window.activeTextEditor and vscode.workspace.fs.readFile (SKILL.md). Boundary markers: None. Capability inventory: vscode.workspace.fs.writeFile and shell task execution. Sanitization: None provided in the reference snippets.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 4, 2026, 01:44 PM
Security Audit — agent-trust-hub — integrating-vscode