Security audit
Security checks for vulnerabilities and agentic risk
This is a content-only entertainment skill for generating fictional alternate-universe responses, with no code execution, persistence, or data access.
Install this if you want humorous fictional 'what if' content. Be aware it may trigger too easily on broad phrases like 'if' or 'what if', and its fake-news style sections should be treated as fiction rather than factual reporting.
The description states the skill should activate whenever the user mentions broad keywords, without defining boundaries or intent checks. In practice, this ambiguous invocation model can make the agent spuriously enter a playful alternate-universe mode during serious, analytical, or safety-sensitive conversations.
The trigger condition activates on very broad phrases like '假如', '如果', 'what if', '脑洞', and '平行宇宙', which are common in normal conversation and not narrowly scoped to this entertainment skill. This can cause unintended invocation, hijack unrelated user requests, and override the expected behavior of the host agent with irrelevant or misleading output.
The instructions require “超详细英文 prompt”, which forces a specific language for part of the output. The file does not offer opt-in, fallback, or user choice for prompt language, so it creates a language-policy concern.
