quiz-maker

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [Prompt Injection] (SAFE): The instructions are focused on quiz generation and do not contain patterns intended to bypass AI safety guards or extract system prompts.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded secrets, API keys, or attempts to access sensitive local files were found.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not include any scripts or package manifest files (e.g., requirements.txt, package.json) and performs no remote downloads.
  • [Indirect Prompt Injection] (SAFE): The skill possesses a data ingestion surface (user-provided quiz topics), but since it has no executable capabilities, network access, or file-writing permissions, this surface cannot be exploited for malicious actions. (Ingestion points: User quiz requests in SKILL.md; Boundary markers: Absent; Capability inventory: None; Sanitization: Absent).
  • [Dynamic Execution] (SAFE): No runtime code generation or dynamic loading patterns are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 05:42 PM