Security audit
Security checks for vulnerabilities and agentic risk
This is a Chinese-language life-advice prompt skill with no code execution, persistence, credential access, or hidden system changes.
Install only if you want a Chinese-language reflective life-mentor style skill. Treat its career, relationship, and values advice as general perspective, and use qualified professional help for crisis, medical, legal, financial, or serious mental-health situations.
The skill is scoped to very broad categories like career, relationships, life meaning, and values without clear activation boundaries or safety limits. This can cause the agent to engage in high-stakes advice situations by default, increasing the risk of unsafe guidance, overreach into mental-health-like counseling, or inappropriate use when specialized support is needed.
The skill is presented entirely in Chinese and describes a Chinese-language persona without stating whether it can adapt to the user's preferred language. While not directly a security flaw, this can reduce user comprehension of important caveats and increase the chance of misunderstanding in sensitive life-advice contexts.
The manifest description is entirely in Chinese and presents the skill as a Chinese-language life-guidance system, with no indication that users can choose another language or locale. This can violate a language/locale policy when the skill implicitly enforces one language without explicit opt-in or documented regional scope.
This markdown file presents all guidance in a single language and does not indicate that users may choose another language or that the Chinese-only format is required for a region-specific purpose. Under the language/locale policy criterion, forcing a specific language without opt-in is a natural-language policy concern.
No suspicious patterns detected.
