Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple writing helper that turns user-provided work descriptions into achievement language, with no code execution, persistence, credential access, or hidden data handling.
This appears safe to install as a writing aid. Be aware that it will likely answer with Chinese section headings unless you ask for another language, and you should still review generated achievement statements for accuracy because the skill is designed to make impact visible without inventing metrics.
The skill metadata explicitly centers a Chinese-only trigger phrase and does not indicate that language should adapt to the user's preference. This can steer interactions into a fixed language mode, reducing usability and potentially causing misunderstanding or inaccessible output for users who did not request Chinese.
The default output pattern hard-codes Chinese headings, which makes the generated response language effectively mandatory unless overridden elsewhere. This is risky from a safety and quality perspective because it can produce confusing or exclusionary outputs for users expecting another language, even though there is no evidence of malicious intent.
This markdown file contains several achievement-writing templates in Chinese and one in English, but does not indicate whether users may choose their preferred language or whether the mixed-language format is intentional. Under the policy rule for language/locale, prescribing content in specific languages without opt-in can be a natural-language policy concern.
No suspicious patterns detected.
