Security audit
Security checks for vulnerabilities and agentic risk
This skill is a narrowly scoped writing helper for making Chinese guided-reading notes from user-provided academic papers, with no evidence of hidden execution, credential use, persistence, or data exfiltration.
Install this if you want Chinese guided-reading documents for academic papers. Be aware that it may be auto-selected for paper-reading guide requests and will naturally read the paper content you provide, including PDFs, URLs, excerpts, abstracts, or LaTeX, but the artifact does not ask for credentials or run code.
The description defines the skill as generating a Chinese guided-reading edition and repeatedly frames Chinese output as the default behavior. This is a natural-language locale constraint, and the file does not state that the user may choose another language or explicitly opt into Chinese beyond the skill name itself.
The skill description hard-codes Chinese output as the default behavior without indicating that the user must opt in to that language. This can lead to unintended language transformation, usability failures, and accidental disclosure or policy mismatches if the content is routed through a skill the user did not knowingly select for translation-style processing.
The skill enables implicit invocation but provides no clear trigger constraints, so the system may auto-select it in situations where the user did not explicitly ask for a Chinese guided-reading transformation. Because this skill can transform user-supplied papers, URLs, excerpts, or LaTeX into a derived document, accidental invocation can cause unwanted data handling, unexpected workflow changes, and user-surprising output behavior.
No suspicious patterns detected.
