asc-revenuecat-catalog-sync
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
asccommand-line tool to perform operations on App Store Connect, including reading catalogs and creating or updating subscription and in-app purchase resources. - [EXTERNAL_DOWNLOADS]: The skill references documentation and tool specifications from RevenueCat's official website, which is a well-known service for mobile subscription management.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external APIs (App Store Connect and RevenueCat) to build reconciliation plans and execute downstream actions, representing a vulnerability surface for indirect instructions embedded in product metadata.
- Ingestion points: Product catalogs and resource lists are read from the
ascCLI (JSON output) and RevenueCat MCP tools in Step A and Step B of the workflow. - Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions when the agent processes the JSON data returned by these external tools.
- Capability inventory: The skill possesses write capabilities, including resource creation and configuration updates in both App Store Connect (via
asc) and RevenueCat (via MCP tools). - Sanitization: There is no explicit requirement for the agent to sanitize or validate metadata (such as reference names or descriptions) retrieved from the APIs before using them in subsequent command parameters or setup calls.
Audit Metadata