hw-ask
Pass
Audited by Gen Agent Trust Hub on Nov 4, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill's primary function is to retrieve and summarize information from its internal knowledge base located in the 'knowledge/' directory.
- [NO_CODE]: The skill uses the 'disable-model-invocation: true' configuration, which prevents the AI agent from calling any tools or executing code during its operation.
- [INDIRECT_PROMPT_INJECTION]: While the skill processes a large volume of external data (interview experiences from Xiaohongshu and community forums), the risk is minimal because the agent lacks any active capabilities (code execution, file writing, or network sending) to exploit. The instructions also enforce strict adherence to the knowledge base and forbid fabrication.
- [DATA_EXFILTRATION]: There are no network operations or sensitive file accesses. All referenced URLs point to well-known or author-owned platforms (codefun2000.com, bilibili.com, feishu.cn) for educational purposes.
- [OBFUSCATION]: Analysis of the instructions and metadata revealed no evidence of hidden characters, encoded commands, or homoglyph attacks.
Audit Metadata