Behavioral Nudge Engine
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes user task queues, which introduces a theoretical surface for indirect prompt injection.
- Ingestion points: The agent ingests external data from the
pendingTasksarray as described in the workflow of SKILL.md. - Boundary markers: The instructions do not explicitly require the use of delimiters or provide directions to ignore instructions that might be embedded within the ingested task text.
- Capability inventory: The skill generates communication for SMS, Email, and In-App channels and suggests automated actions, such as sending drafted replies, although it includes user approval checkpoints.
- Sanitization: No specific methods for validating or sanitizing the content of the task queue are defined in the instructions.
Audit Metadata