teacher-inquiry-cycle-designer

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection. User-supplied variables such as inquiry_question and teacher_context are embedded directly into the expert prompt. An adversarial user could potentially use these fields to provide instructions that attempt to redirect the agent's behavior beyond the intended educational scope.
  • Ingestion points: External data enters the agent context via the inquiry_question and teacher_context input fields defined in SKILL.md.
  • Boundary markers: There are no delimiters (such as XML tags or triple quotes) or explicit 'ignore embedded instructions' warnings surrounding the interpolated variables to help the model distinguish between instructions and data.
  • Capability inventory: The skill is limited to text generation; analysis of the YAML frontmatter and markdown body reveals no use of tools, network operations, file system writes, or subprocess execution.
  • Sanitization: No sanitization, escaping, or validation logic is present to process or filter the user-provided content before it is processed by the model.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:23 AM
Security Audit — agent-trust-hub — teacher-inquiry-cycle-designer