onboarding-questions

Pass

Audited by Gen Agent Trust Hub on Nov 3, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches external content such as App Store reviews and descriptions using curl. This content is used to inform the agent's generation of onboarding copy and logic, creating a surface for indirect prompt injection. * Ingestion points: SKILL.md fetches data from itunes.apple.com via RSS feeds and lookup APIs. * Boundary markers: There are no explicit instructions or delimiters used to isolate or ignore potential prompts within the external data. * Capability inventory: The skill utilizes curl for network access, jq for data processing, and provides instructions for npx-based skill installation. * Sanitization: The skill does not implement validation or sanitization of the fetched external strings.
  • [EXTERNAL_DOWNLOADS]: The skill references and provides instructions to install additional components from the developer's official GitHub repository (github.com/superwall/skills).
  • [COMMAND_EXECUTION]: The skill uses shell commands like curl and jq to perform app research and recommends using npx with a bypass flag (--yes) for automated skill installation.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 3, 2026, 12:18 AM