Security audit
Security checks for vulnerabilities and agentic risk
This is a content-only spirituality support skill with some scope and language-quality caveats, but no hidden code, persistence, credential access, or unsafe execution behavior.
This skill is reasonable to install for grounded Chinese-language discussion of enlightenment and related spiritual experiences. Before using it, be aware that it is not a mental-health or spiritual-authority substitute, and its publisher should ideally clarify language behavior and tighten the off-topic lifestyle-coaching example.
The title and all example scenarios are presented primarily in Chinese, and the README does not indicate that users may interact in other languages or choose their preferred locale. This can violate a language/locale policy when a skill effectively assumes a specific language without opt-in or justification.
The manifest describes a skill for grounded explanation and reflection on enlightenment-related concepts, awakening-like experiences, and spiritual misconceptions. L029-L031 instead prescribe advice about public-account content, unfollowing bloggers, and recommending unrelated information sources and weekly self-review templates, which is broader lifestyle coaching rather than enlightenment-topic support.
The file scopes usage to cases where the user asks what the Chinese term "开悟" means, and the content heavily relies on Chinese terminology and examples throughout. There is no indication that the skill offers a language choice or asks whether the user wants explanations in Chinese versus another language, which can be a locale/language policy concern.
The file includes hardcoded response text in Chinese ('Say: ...') without indicating that this should depend on the user's language or preference. This can override user expectations, reduce usability, and in some settings create trust or safety issues if the user cannot understand important nuance, especially in a psychologically sensitive spiritual-support context.
This markdown file presents all user/example content solely in Chinese and does not indicate that the skill is region-specific or that users can opt into the language. Under the language/locale policy rule, forcing a specific language without user choice can be a natural-language policy violation.
This markdown file contains multiple Chinese headings and user-facing prompts, but nowhere indicates that the skill is Chinese-only or that the user can choose a preferred language. Under the policy, forcing a specific language without opt-in is a natural-language policy violation.
The mode headings and all example user utterances are written in Chinese, which signals the skill is designed around a single language. The file does not state that Chinese is optional, user-selected, or required for a justified region-specific purpose, so it appears to force a specific language without opt-in.
This markdown file contains the skill's acceptance criteria and user-facing test inputs in Chinese, but nowhere indicates that the skill is Chinese-only or that users may choose another language. That can amount to an implicit language policy constraint without user opt-in.
The guidance and example phrasings are predominantly written in Chinese and present fixed response formulations in that language, which can steer the skill to answer in Chinese regardless of the user's preferred language. This is a natural-language locale policy concern because the file does not offer a language choice or document that the skill is intentionally region- or language-specific.
No suspicious patterns detected.
