document-based-lesson-designer
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or data exfiltration attempts were detected.
- [NO_CODE]: This skill is entirely comprised of instructions and metadata. It does not contain any executable scripts, binary files, or external package dependencies, which significantly limits its potential for malicious action.
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it interpolates user-provided data (central_question, document_set) directly into the agent prompt without using delimiters or sanitization. However, because the skill has no access to sensitive tools or file systems, the impact of such an injection is negligible.
- [PROMPT_INJECTION]: Mandatory Evidence Chain for Indirect Prompt Injection:
- Ingestion points: SKILL.md (fields: central_question, document_set, student_level, lesson_duration)
- Boundary markers: Absent
- Capability inventory: None (No tools or code execution)
- Sanitization: Absent
Audit Metadata