Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward learning aid that maps experts and sources for a chosen domain without hidden code, persistence, credential use, or unsafe actions.
Installers should expect the skill to guide the agent toward research-style answers and possibly web/source verification for current or contested fields. Review the output language and citations for fit, but the artifact does not show hidden execution or sensitive access.
All user-facing fields in the manifest are written in Chinese, which implies a fixed language experience without indicating user opt-in or a region-specific justification. This can violate language/locale policy when the skill does not explicitly offer a language choice.
The manifest's default prompt is a generic natural-language request for quickly learning any domain, which overlaps with common user phrasing and does not define when this skill should or should not activate. The file provides no explicit trigger scope, exclusions, or negative examples to prevent unintended invocation.
The README presents core usage and output content in both Chinese and English, but it does not tell users what language the skill will use or offer an explicit language preference choice. This can violate language/locale policy expectations because the skill appears to impose or assume language behavior without user opt-in.
No suspicious patterns detected.
