The Agent Skills Directory

[SAFE]: The skill is purely informational and contains no executable scripts (Python, JavaScript, or Shell) that could perform unauthorized actions.
[SAFE]: Instructions in SKILL.md are strictly focused on data retrieval and formatting, directing the agent to use only provided knowledge files and citing sources like Bilibili and CodeFun2000.
[SAFE]: All external links point to legitimate educational and career platforms, including the vendor's own resource codefun2000.com, as well as leetcode.cn, nowcoder.com, and bilibili.com.
[SAFE]: No evidence of prompt injection, data exfiltration, or privilege escalation was found during the analysis of the 199 files.
[SAFE]: The use of disable-model-invocation: true in the frontmatter acts as a safety restriction, preventing the model from autonomously calling tools unless explicitly configured.

hw-ask