asc-app-create-ui

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted input (such as app name, SKU, and bundle ID) and uses these values to drive a browser automation session on the App Store Connect website.
  • Ingestion points: Input parameters including app name, bundle ID, SKU, and primary language derived from user requests or external context (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific safety instructions to prevent the agent from interpreting content within these inputs as new instructions.
  • Capability inventory: The skill utilizes browser automation tools (Playwright/MCP) and local shell execution for the asc CLI, providing a high-privilege execution environment.
  • Sanitization: No explicit sanitization, character escaping, or validation logic is specified for the input data before it is filled into the web forms.
  • [COMMAND_EXECUTION]: The skill relies on the execution of various local shell commands using the asc CLI (e.g., asc bundle-ids create, asc apps list, asc pricing availability create) to perform preflight checks and post-creation configuration.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 09:27 PM