hz-store-submit

Pass

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an attack surface where untrusted user input is interpolated into shell commands. \n
  • Ingestion points: User-provided values for <package>, path/to/release.apk, <APP_ID>, and <APP_SECRET> are used in shell commands in SKILL.md and references/rejection-troubleshooting.md. \n
  • Boundary markers: The instructions lack explicit delimiters or warnings to ignore embedded instructions in the provided parameters. \n
  • Capability inventory: The skill utilizes high-capability tools including metavr for device interaction (adb, install, launch) and ovr-platform-util for uploading data to remote servers. \n
  • Sanitization: There is no evidence of input validation or sanitization for the provided strings before they are passed to the shell.\n- [COMMAND_EXECUTION]: The skill relies on executing shell commands through metavr and ovr-platform-util. These tools are recognized as standard for the Meta Quest development ecosystem and align with the skill's stated purpose of store submission management.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 25, 2026, 06:57 PM
Security Audit — agent-trust-hub — hz-store-submit