curriculum-knowledge-architecture-designer

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to the ingestion of untrusted curriculum data.
  • Ingestion points: Data is pulled from the existing_curriculum_documents, competency_framework, and prior_knowledge_baseline fields in SKILL.md.
  • Boundary markers: The system prompt does not use delimiters or explicit instructions to isolate user-provided content from the agent's instructions.
  • Capability inventory: The skill has no high-risk capabilities; it is limited to text generation and has no access to the shell, network, or external file system.
  • Sanitization: No validation or sanitization is applied to the curriculum inputs before they are included in the prompt context.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 10:53 PM