ruler-emotional-literacy-sequence
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill was evaluated across all 10 threat categories and no malicious patterns, obfuscation, or dangerous commands were identified. It functions exclusively as a text-generation prompt for educational purposes.
- [SAFE]: Analysis of the indirect prompt injection surface (Category 8) indicates that while the skill ingests untrusted user input via placeholders (e.g., {{emotional_context}}), the agent has no associated capabilities (allowed-tools is empty, no scripts provided) to abuse. The risk of unintended behavior is limited to the content of the generated response. Evidence Chain: 1. Ingestion points: emotional_context, student_profiles, student_level, subject_area, time_available, ruler_familiarity in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: None. 4. Sanitization: Absent.
Audit Metadata