cognitive-tutoring-architecture-designer

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security risks were detected. The skill is a specialized prompt for educational design, focusing on knowledge component mapping and mastery tracing.
  • [SAFE]: The skill does not request or use any external tools, APIs, or network resources. The use of disable-model-invocation: true in the frontmatter serves as a security best practice by limiting the agent's execution scope.
  • [SAFE]: No evidence of prompt injection, obfuscation, or persistence mechanisms was found. The skill uses benign instructional language and provides structured, academic-focused guidance.
  • [SAFE]: While the skill ingests user-provided text for skill_domain and knowledge_components, it lacks any executable capabilities (such as shell access or file writing) that would allow an attacker to leverage indirect prompt injection for malicious purposes. The output is limited to descriptive design documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 04:53 AM