subscription-lookup
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data originating from Zoho Billing API responses and user-supplied arguments. This creates a theoretical surface where malicious instructions could be embedded in billing records (e.g., customer names or invoice notes).
- Ingestion points: The skill accepts user input via the
$ARGUMENTSvariable and fetches data from theZohoBilling_Get_a_Subscription,ZohoBilling_Search_Customers,ZohoBilling_List_all_Invoices, andZohoBilling_List_all_Paymentstools. - Boundary markers: The instructions do not define explicit delimiters or warnings to ignore instructions embedded in the retrieved data.
- Capability inventory: The skill is restricted to read-only tool invocations and has no capabilities for file system modification, arbitrary command execution, or external network requests outside the Zoho toolset.
- Sanitization: There is no explicit sanitization or filtering logic mentioned for the external content before it is displayed to the user.
Audit Metadata