gplay-metadata-sync
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes natural language text (app titles and descriptions) from the Google Play API, which is an external and potentially attacker-controlled source.
- Ingestion points: Data enters the agent's context through the
gplay metadata pullcommand, which populates the local./metadatadirectory with content from Play Store listings (SKILL.md). - Boundary markers: No specific delimiters or instructions are provided to the agent to treat the content of these metadata files as untrusted or to ignore embedded instructions.
- Capability inventory: The skill possesses the ability to write to the local file system (
pull) and perform network-based updates to the live Play Store listing (apply --confirm). - Sanitization: The instructions do not describe any sanitization, filtering, or validation mechanisms for the fetched text content.
- [COMMAND_EXECUTION]: The skill uses shell commands and CLI tools (
gplay,jq) to perform its synchronization tasks. It also mentions the environment variableGPLAY_ALLOW_EXTERNAL_SYMLINKS=1, which, when enabled, allows the tool to follow symlinks to files located outside the intended project tree, expanding the scope of accessible files.
Audit Metadata