gplay-submission-checks
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions.
- Ingestion points: Reads app-release.aab (via gplay preflight), metadata files in ./metadata, and JSON configuration files like data-safety.json and release-notes.json.
- Boundary markers: The instructions do not specify the use of delimiters or clear separation between data and instructions when processing these files.
- Capability inventory: The skill utilizes the gplay CLI, which has capabilities for file system access and network operations for interacting with Google Play APIs.
- Sanitization: There is no mention of sanitizing or escaping the content of metadata or configuration files before they are processed by the agent or the CLI tools.
Audit Metadata