pipeline-forecasting
Pass
Audited by Gen Agent Trust Hub on Feb 13, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill is designed to process untrusted sales data, which creates a potential surface for indirect prompt injection to influence agent reasoning.\n
- Ingestion points: Sales pipeline data provided via user input as described in the 'How to Use' section of SKILL.md.\n
- Boundary markers: Absent; data is interpolated directly into instructions without delimiters.\n
- Capability inventory: Limited to internal mathematical calculations and agent reasoning; no file-system, network, or command-execution capabilities are present.\n
- Sanitization: Absent.\n- [No Code] (SAFE): The skill consists entirely of natural language instructions and does not execute any code, scripts, or binary files.
Audit Metadata