document-based-lesson-designer

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is a purely instructional prompt designed for educational lesson planning. It does not perform any file system operations, network requests, or command execution.
  • [PROMPT_INJECTION]: The skill ingests untrusted data through input fields like document_set and central_question and interpolates them directly into the system prompt. There are no boundary markers (e.g., XML tags or delimiters) or explicit 'ignore instructions' warnings used to wrap these inputs. This creates a surface for indirect prompt injection; however, because the skill has no tool-use capabilities or dangerous side effects, the risk is minimal.
  • [DATA_EXFILTRATION]: No network tools or commands capable of exfiltrating data are used or requested in the frontmatter.
  • [CREDENTIALS_UNSAFE]: No hardcoded credentials or access to sensitive environment variables were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 03:20 AM