Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only Chinese divination skill with no hidden code, network access, credentials, or persistence, but users should not rely on it for medical, legal, or financial decisions.
Install only if you intentionally want Chinese 奇门遁甲-style readings. Treat outputs as entertainment or cultural reference, not as medical diagnosis, treatment guidance, legal advice, investment advice, or a substitute for professional help. Consider invoking it explicitly by name to avoid accidental use on ordinary advice questions.
The README presents the skill entirely in Chinese and does not indicate that users may choose another language for interaction or output. Under the policy, a language constraint should either be optional for the user or explicitly documented and justified as region-specific; neither is stated here.
The example trigger phrases are broad, natural-language requests such as asking about projects, travel, or job changes, which can overlap with ordinary user conversation and cause the skill to activate unintentionally. In an agent environment, overbroad invocation increases prompt-surface area and can route unrelated user queries into this skill, leading to confusing behavior, unwanted horoscope-style advice, or interference with higher-priority skills.
The trigger list includes broad phrases like “问事业”, “看看时盘”, and “断卦判断” that can overlap with ordinary user conversation, making accidental or unsolicited activation more likely. In an agent setting, this can cause the skill to take over unrelated chats and produce deterministic advice in contexts where the user did not explicitly consent to divination-style guidance.
The quick-start and invocation examples encourage broad natural-language activation without strong constraints, reinforcing a behavior where many loosely related prompts may trigger the skill. Because the skill is designed to answer directly and authoritatively, accidental activation can misroute user requests and override safer domain-specific handling.
The skill explicitly supports health and disease-related readings (“疾病”, “健康”) but does not place a prominent safety warning or escalation rule near that guidance. Since the skill also instructs the agent to speak decisively and avoid uncertainty, it could provide authoritative pseudo-medical advice that delays appropriate clinical care or misleads users during urgent health situations.
No suspicious patterns detected.
