exam-planner

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is entirely instruction-based and does not contain any executable scripts, binary files, or external code dependencies. Its primary function is to guide the agent through a four-step planning process.
  • [DATA_EXPOSURE]: There are no patterns indicating access to sensitive file paths, environment variables, or hardcoded credentials. The data collected from the user (school and grade self-evaluation) is used only to populate the output template.
  • [REMOTE_CODE_EXECUTION]: No remote script downloads or dynamic code execution patterns were detected. The search step uses template-driven queries for public information like exam scores and admission ratios.
  • [PROMPT_INJECTION]: The instructions do not contain markers for bypassing safety filters, overriding system instructions, or extracting system prompts. It includes a 'Quality Redline' section that enforces ethical behavior such as not promising unrealistic results and avoiding cheating methods.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 02:56 PM
Security Audit — agent-trust-hub — exam-planner