gpc-multi-app
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/detect_gpc.mjsexecutes shell commands usingexecSyncto verify the status of the GPC CLI tool. The commands, such asgpc --versionandgpc auth status, are hardcoded and used for diagnostic purposes.\n- [EXTERNAL_DOWNLOADS]: The skill refers to and usesnpxto run the@gpc-cli/cliandgpcpackages. This results in the automatic download and execution of these packages from the npm registry if they are not already installed locally.\n- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it is designed to ingest and act upon configuration data found in.gpcrc.jsonfiles located within the user's project structure.\n - Ingestion points: The skill reads project-level
.gpcrc.jsonfiles, the global~/.config/gpc/config.jsonfile, and environment variables such asGPC_APPandGPC_PROFILE.\n - Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish between configuration data and instructions within these files.\n
- Capability inventory: The agent, via the
gpcCLI, can perform sensitive operations on the Google Play Store, including managing releases, uploading application bundles, and modifying store metadata.\n - Sanitization: The skill does not implement any validation or sanitization of the configuration values before they are used to execute shell commands.
Audit Metadata