Security audit
Security checks for vulnerabilities and agentic risk
This skill only teaches agents to report back when background work finishes, and it contains no executable code, credential access, or persistence.
Install this if you want agents to proactively deliver results from background work. Review the wording if you prefer agents not to default tool work into background execution, or if you need acknowledgment examples that always match the user's language.
The examples for the required start acknowledgment are exclusively in Chinese, presented as the canonical pattern agents should send. Because the document otherwise applies generally and does not state that this is only for Chinese-speaking users or offer a language choice, it imposes a locale/language behavior without user opt-in.
The section labeled as a minimal Chinese version instructs how to teach the behavior to a Chinese agent, but the overall skill is not clearly limited to Chinese-language use cases. Without explicit scoping that output should follow the user's preferred language, this creates a language policy risk by steering agent behavior toward a specific language.
No suspicious patterns detected.
