optimization-mode-router
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill manages a workflow that involves the ingestion of external data provided by users for optimization modeling (e.g., CSV files). This creates a surface for indirect prompt injection where instructions hidden within the user data could attempt to influence the agent's behavior during the model formulation or solving process.
- Ingestion points: User-provided data for scheduling, assignment, allocation, and routing problems (SKILL.md).
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the processed data.
- Capability inventory: The logic hands off to powerful tools including Python APIs and CLI tools for numerical and routing optimization.
- Sanitization: No specific data sanitization or validation steps are outlined in the routing logic, although the skill requires the use of a sandbox environment for subsequent execution steps.
Audit Metadata