Security audit
Security checks for vulnerabilities and agentic risk
This is a prompt-only weekly report generator; its main risk is that users may paste sensitive work details, but the package discloses this risk in the README and contains no executable behavior.
Before using it, avoid pasting secrets, customer names, HR records, exact financial figures, source code, or other confidential internal details unless your organization permits that AI tool. Prefer anonymized names and approximate or redacted figures.
The entire skill is written as a Chinese-only prompt and all example interactions and output templates are presented in Chinese, with no indication that the user may choose another language. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.
The skill explicitly encourages users to paste detailed weekly work information into an AI chat, which can easily include personal data, internal project details, customer names, revenue figures, HR information, or other confidential business content. Because there is no privacy warning, minimization guidance, or redaction instruction, users may overshare sensitive information into an external system without understanding the risk.
No suspicious patterns detected.
