awe-wonder-experience-designer

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely informational and focused on pedagogical design. It does not perform any network requests, file system operations, or command executions.
  • [SAFE]: No hardcoded credentials, sensitive file paths, or obfuscated content were detected in the skill's instructions or metadata.
  • [INDIRECT_PROMPT_INJECTION]: The skill accepts several user-controlled inputs, such as lesson_content and student_profiles, which are interpolated directly into the prompt without explicit delimiters or sanitization instructions. While this represents a theoretical attack surface for indirect prompt injection, the skill's lack of executable capabilities (like shell access or network tools) minimizes the potential impact to harmless output manipulation.
  • Ingestion points: Inputs lesson_content, student_level, subject_area, awe_trigger, student_profiles, available_resources, and lesson_duration in SKILL.md.
  • Boundary markers: Absent. The prompt uses markdown headers but no specific 'ignore embedded instructions' delimiters for the user inputs.
  • Capability inventory: No subprocess calls, file operations, or network tools are requested or used.
  • Sanitization: No specific sanitization or validation logic is applied to the input fields.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 10:53 PM