agent-generator-tutor

Pass

Audited by Gen Agent Trust Hub on Mar 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by processing untrusted user input while having access to system tools.
  • Ingestion points: User responses are ingested through functions like check_exercise and run_quiz.
  • Boundary markers: No explicit markers or isolation instructions are defined in the skill documentation.
  • Capability inventory: The skill utilizes Bash and Read tools, and describes capabilities for spawning agents and generating code patches.
  • Sanitization: No sanitization or validation of user input is specified.
  • [COMMAND_EXECUTION]: The curriculum involves dynamic code assembly and execution through 'Math Code Gen' (Lesson 12) and 'Patch Proposer' (Lesson 13) features. These operations use the allowed Bash tool to perform their primary educational functions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 14, 2026, 03:25 PM