gplay-metadata-sync
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions for the agent to execute shell commands using a utility named
gplay. These commands include actions likesync export-listings,sync import-listings,images upload, anddetails update, which interact with external services and the local filesystem. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and upload content from local files such as
title.txt,short_description.txt, andfull_description.txtlocated in thefastlane/metadata/android/directory. - Ingestion points: Content is ingested from local text files when the agent runs commands like
gplay sync import-listings --dir ./fastlane/metadata/androidorgplay listings update. - Boundary markers: The skill does not define specific boundary markers or instructions to treat the file content strictly as data, which might allow instructions embedded in the metadata to be interpreted by the agent.
- Capability inventory: The agent has capabilities to execute shell commands, read/write local files, and interact with the Google Play Store API via the
gplaytool. - Sanitization: There are no visible sanitization or validation steps to ensure that the content of the metadata files does not contain malicious instructions or unexpected control characters before being processed.
Audit Metadata