gps-monetization
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses a custom CLI tool named
gpsto interact with monetization catalogs. It executes shell commands likegps subscriptions listandgps ops offer. Some commands utilize environment variables (e.g.,$PKG) for package identification and construct JSON payloads using shell string interpolation, which can be prone to formatting errors or injection if variables are not strictly controlled. - [PROMPT_INJECTION]: The skill ingests monetization data from external Google Play Store APIs, creating a potential surface for indirect prompt injection if product metadata contains malicious instructions.
- Ingestion points: Data returned from commands such as
gps subscriptions list,gps subscriptions get,gps otp list, andgps iap list(SKILL.md). - Boundary markers: There are no explicit delimiters or boundary markers used to separate external data from the agent's instructional context.
- Capability inventory: The skill allows for listing, getting, and patching monetization data, including pricing and product configuration, using the
gpstool (SKILL.md). - Sanitization: No evidence of data sanitization, schema validation, or escaping is provided for the content retrieved from external APIs.
Audit Metadata