Security audit
Security checks for vulnerabilities and agentic risk
This is a text-only Chinese lyric-writing helper with disclosed limits and no evidence of hidden access, persistence, networking, or destructive behavior.
Install this if you want a Chinese-oriented lyric and rhyme assistant. Expect outputs to default to Chinese pop/folk/rap/guofeng structures and Chinese rhyme conventions; if you need multilingual lyric writing, this skill may be too narrow without adaptation.
The trigger list includes very generic phrases such as "lyrics" and broad lyric-writing requests, which can cause the skill to activate during ordinary multilingual conversation rather than only when a user explicitly wants this workflow. This is not a direct security exploit, but it can lead to unintended routing, context capture, or interference with higher-priority skills.
The documented trigger set lacks clear activation boundaries and includes ambiguous phrases that may match common user utterances beyond the intended lyric-writing use case. In an agent ecosystem, this increases the risk of accidental invocation, misrouting user requests, and exposing user inputs to a skill that was not actually needed.
This markdown file is entirely framed in Chinese and defines lyric-writing defaults such as Chinese character counts per line, rhyming conventions, and genre rules as the default structure. There is no indication that the user can choose another language or locale, which can constitute a language/locale policy violation under the rule for natural-language policy concerns.
The template is entirely specified in Chinese and requires Chinese-specific constraints such as counting Han characters and using the '十三辙' rhyme system. This effectively mandates a single language/locale for output, with no indication that users may choose another language or locale.
The title and entire content are presented only in Chinese, and there is no indication that the skill is intentionally region- or language-specific or that users can opt into another language. Under the policy, forcing a specific language without user choice can be a natural-language policy violation.
