cash-flow-forecasting

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for Indirect Prompt Injection because it processes data from external untrusted sources.\n
  • Ingestion points: Step 1 explicitly fetches historical and plan data from [ERP], [OA], and [BK] systems (SKILL.md).\n
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore or isolate potential instructions embedded within the fetched data.\n
  • Capability inventory: The skill is primarily designed for data aggregation and report generation; it does not contain active commands like file writes or network operations.\n
  • Sanitization: There is no evidence of sanitization or validation of the input data before it is interpolated into the forecasting models.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:25 AM
Security Audit — agent-trust-hub — cash-flow-forecasting