word
Pass
Audited by Gen Agent Trust Hub on Apr 19, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a text-formatting template for pedagogical purposes and does not request or use any sensitive capabilities or tools.
- [DATA_EXFILTRATION]: The instructions explicitly prohibit the writing of local files ("不要写本地文件"), ensuring that the agent's output remains within the conversation context and does not interact with the host file system.
- [REMOTE_CODE_EXECUTION]: The skill does not contain any instructions for downloading external code, installing packages, or executing shell commands.
- [PROMPT_INJECTION]: The content is focused on defining a specific output structure and does not contain patterns intended to bypass safety guardrails or override system-level instructions.
Audit Metadata