gongkao-huasheng13

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists exclusively of educational Markdown files. It functions as a knowledge base for exam strategies and does not include any executable code, scripts, or binary files.
  • [DATA_EXFILTRATION]: There are no network-related commands (e.g., curl, wget) or attempts to access sensitive local files or environment variables. All external links in the documentation point to well-known educational platforms or official government exam sites.
  • [PROMPT_INJECTION]: The instructions in SKILL.md and README.md are focused on educational workflows. There are no patterns suggesting attempts to bypass safety filters, extract system prompts, or override agent constraints.
  • [REMOTE_CODE_EXECUTION]: No remote code execution patterns or unverifiable third-party dependencies were detected. The skill does not perform runtime package installations or script execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 03:16 AM
Security Audit — agent-trust-hub — gongkao-huasheng13