app-store-aso

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: Potential for indirect prompt injection. The skill is designed to ingest and analyze external app listings and competitor data, which represents an untrusted data surface.
  • Ingestion points: SKILL.md directs the agent to analyze the app context, features, and competitor listings.
  • Boundary markers: The instructions lack delimiters or explicit warnings to ignore potential instructions embedded within the analyzed app data.
  • Capability inventory: The agent has the ability to execute a local Python validation script and the krankie CLI tool.
  • Sanitization: No validation or sanitization of the external app data is performed before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill documentation includes instructions to install the krankie CLI tool using bun install -g krankie. This is a vendor-provided tool used for tracking keyword rankings on the App Store.
  • [COMMAND_EXECUTION]: The skill involves the execution of various shell commands to perform its duties:
  • It runs python scripts/validate_metadata.py to verify that generated recommendations meet Apple's character limits.
  • It uses the krankie CLI tool for app management, keyword tracking, and ranking analysis.
  • It provides a command (krankie cron install) to establish a daily cron job for automated ranking updates.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 12:31 PM