shenlun-mingshi
Pass
Audited by Gen Agent Trust Hub on Jul 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional Markdown files focused on exam preparation. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. All content is educational and relates to civil service exam techniques.
- [NO_CODE]: There are no executable scripts (Python, Node.js, Shell, etc.) or external dependencies included in the skill. The logic is handled through natural language instructions for the agent.
- [DATA_EXPOSURE_AND_EXFILTRATION]: No network operations (e.g., curl, wget, fetch) or sensitive file path access (e.g., .ssh, .aws) were found in the skill files. All data processing is local and informational.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes user-supplied exam questions as untrusted data, it lacks exploitable capabilities like command execution, file system modifications, or network exfiltration. The risk is minimized as the output remains within an educational tutoring context.
Audit Metadata