Behavioral Nudge Engine
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-controlled data to generate actionable nudges.
- Ingestion points: External task data (pendingTasks) and user profile information (userProfile) are ingested during the Phase 2 (Task Deconstruction) and Phase 3 (The Nudge) workflows.
- Boundary markers: The skill instructions do not define delimiters or explicit warnings for the agent to ignore instructions embedded within the task content.
- Capability inventory: The skill facilitates the generation and delivery of content for SMS, Email, and In-App communication channels.
- Sanitization: No instructions are provided for sanitizing or filtering the content of ingested tasks before they are processed into nudges.
Audit Metadata