skills/laststance/skills/feature-tour/Gen Agent Trust Hub

feature-tour

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to manage development environments, launch Chrome with specific debugging flags, and control UI interactions through playwright-cli. These actions are intrinsic to the functionality of creating a live tour and are explicitly described in the documentation.
  • [EXTERNAL_DOWNLOADS]: Recommends the installation of the @playwright/cli package from the official NPM registry. Playwright is a reputable and well-known browser automation tool from a trusted vendor.
  • [DATA_EXFILTRATION]: The skill communicates with the vscode-debug-mcp-bridge via 127.0.0.1:7779. This network activity is confined to the local loopback address; no sensitive data exfiltration to external domains was detected.
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface as the skill ingests untrusted data from git diff and GitHub PR descriptions (Step 1) to determine tour stops. While no specific boundary markers or sanitization are mentioned for this input, this is an inherent risk of the skill's primary code-analysis purpose and is considered safe in this context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 12:49 PM
Security Audit — agent-trust-hub — feature-tour