app-store-aso
Warn
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPERSISTENCEINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to install a third-party global Node.js package named 'krankie' using the 'bun install -g' command.
- [REMOTE_CODE_EXECUTION]: The skill uses 'bunx krankie', which downloads and executes code from the public NPM registry at runtime without specific version pinning.
- [PERSISTENCE]: The instructions include the 'krankie cron install' command, which modifies the host system's crontab to ensure daily background execution of the tracking tool.
- [COMMAND_EXECUTION]: The agent is directed to execute shell commands to run local Python validation scripts and interact with the 'krankie' command-line interface.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted application data, such as app names and descriptions, to generate its recommendations.
- Ingestion points: The 'Analyze the App Context' step in SKILL.md where the agent reads external app listings.
- Boundary markers: None are defined to separate user-provided data from the skill's operational logic.
- Capability inventory: The skill has the ability to execute shell commands and Python scripts.
- Sanitization: No input validation or sanitization routines are provided to handle potentially malicious directives embedded in the app metadata.
Audit Metadata