Security audit
Security checks for vulnerabilities and agentic risk
This is mostly a static Buddhism reference skill, but it also includes unrelated personal profile, contact, and OpenClaw promotional content that users may not expect.
Review this skill before installing if you want a narrowly focused Buddhism reference. It has no code or system access, but it may cause agents to include unrelated personal contact or OpenClaw promotional information unless the skill is edited or split into separate Buddhism and profile/project skills.
The activation description is broad enough that many ordinary mentions of Buddhist terms could trigger the skill, even when the user's goal is different. Overbroad routing can inject irrelevant instructions or content into conversations, increasing the chance of unintended disclosures from the unrelated profile/promotional sections.
The description states this is a Chinese-English version skill, and the document consistently frames content in those two languages only. There is no indication that users can choose other languages or opt in to a locale restriction, which may conflict with language-choice policy expectations.
The skill is presented as a Buddhism information resource, but a substantial section pivots into unrelated personal profile and OpenClaw project promotion. This creates scope confusion and can cause the agent to disclose or prioritize unrelated personal/business content when users intended to ask about religion or culture, violating least-surprise and increasing prompt-surface for data leakage or covert promotion.
The file contains direct personal contact information and external promotional links unrelated to the stated Buddhism-teaching purpose. In an agent setting, this can lead to unnecessary disclosure of personal data, unsolicited promotion, or steering users to third-party services without clear user intent.
The usage instructions enumerate broad trigger topics without boundaries and explicitly include Chen Lang's profile and OpenClaw matrix as response topics. This widens the skill's response scope beyond its declared purpose and increases the likelihood that unrelated personal/promotional content is surfaced during normal Buddhist-topic queries.
No suspicious patterns detected.
