revenue-reporting
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting untrusted external data, which creates a surface for indirect prompt injection.
- Ingestion points: Workflow Step 4 specifies that the agent should ingest and process external files including billing/GL revenue exports and CRM bookings.
- Boundary markers: The instructions do not include boundary markers or explicit directives for the agent to ignore instructions that might be embedded within the imported data.
- Capability inventory: The skill explicitly leverages the agent's execution harness to run scripts on the provided data.
- Sanitization: No sanitization or validation logic is defined to check the data before it is processed by the agent.
- [DYNAMIC_EXECUTION]: The skill involves the dynamic generation and execution of code at runtime.
- Workflow Step 4 directs the agent to script data bridges and reconciliation tasks using its code execution capabilities based on user-provided file exports.
Audit Metadata