gplay-games
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute gplay CLI commands to list, view, create, and modify game resources. This includes operations that write to draft configurations or remove items.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from Google Play Services when viewing achievement or leaderboard details.
- Ingestion points: Data returned by gplay games achievements/leaderboards view --output json.
- Boundary markers: No explicit delimiters are specified for retrieved external data.
- Capability inventory: Shell command execution via the gplay tool for resource management.
- Sanitization: No sanitization or filtering is defined for the external descriptions or names retrieved from the API.
Audit Metadata