implementation-intention-designer
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and generates text based on a fixed prompt template. It does not contain any executable code or scripts.- [SAFE]: No external dependencies, package installations, or remote code execution patterns were detected. All content is static text.- [SAFE]: The skill does not have capabilities for network communication or sensitive file system access, preventing data exfiltration or credential theft.- [SAFE]: While the skill ingests untrusted user input via multiple fields (e.g., target_behaviour, student_profiles) which creates a surface for indirect prompt injection, the lack of tool access or dangerous capabilities mitigates any security risk. 1. Ingestion points: target_behaviour, student_level, current_barrier, context, student_profiles, subject_area, time_horizon in SKILL.md. 2. Boundary markers: Absent. 3. Capability inventory: Text generation only. 4. Sanitization: Absent.
Audit Metadata