Security audit
Security checks for vulnerabilities and agentic risk
The skill is mostly a prompt-engineering guide, but its portrait-replication instructions conflict with its stated safety boundary and could encourage close likeness copying.
Review before installing. The skill has no code execution or persistence, but it should not be used to recreate real people, copyrighted characters, trademarks, or other identity-sensitive likenesses from reference images unless the use is clearly authorized and allowed by the target platform.
The skill content is entirely written in Chinese and the '反AI腔' section prescribes a fixed response style, but nowhere offers users a language or locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
The skill states it will not output prompts for copying real-person likenesses, but later advises that using a reference image can raise likeness replication to 85%+, which materially enables identity-focused generation. That contradiction weakens the safety boundary and could help users recreate or closely imitate real people despite the earlier prohibition.
The document states that Suno uses '英文标签', which imposes a language requirement in natural-language guidance. This is a locale/language constraint presented as mandatory without offering user opt-in or explaining why the restriction is necessary.
The line '英文自然语言场景描述' specifies a required language for prompts. Under the policy, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.
The guidance '英文场景描述' imposes a specific language requirement. The document does not provide user choice or explain that this is a necessary platform-specific constraint.
No suspicious patterns detected.
