cashflow-forecaster

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill acts as a data processor for external files (CSV, Excel, JSON), which constitutes an indirect prompt injection surface.
  • Ingestion points: Project data and parameters are ingested from user-provided files or direct input as described in instructions.md.
  • Boundary markers: The instructions do not define specific delimiters to isolate user-provided data from agent instructions.
  • Capability inventory: The skill utilizes filesystem permissions (defined in claw.json) to manage project data and export reports.
  • Sanitization: No specific input sanitization or structured schema validation is defined in the provided instructions for external data streams.
  • [SAFE]: All logic is implemented in a transparent Python class using standard libraries. The skill requires no external dependencies and maintains all operations within the user's provided project context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 04:28 AM