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 gps to interact with monetization catalogs. It executes shell commands like gps subscriptions list and gps 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, and gps 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 gps tool (SKILL.md).
  • Sanitization: No evidence of data sanitization, schema validation, or escaping is provided for the content retrieved from external APIs.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 31, 2026, 02:45 PM
Security Audit — agent-trust-hub — gps-monetization