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.mddirects 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
krankieCLI 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
krankieCLI tool usingbun 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.pyto verify that generated recommendations meet Apple's character limits. - It uses the
krankieCLI 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