Security audit
Security checks for vulnerabilities and agentic risk
This skill is a focused complaint-handling assistant that drafts structured Linear comments and does not include hidden execution, persistence, or data-exfiltration behavior.
Before installing, confirm that your support team wants Chinese default comment templates and that agents should only write to Linear when explicitly performing complaint handling. Review drafted customer replies before sending, especially for refunds, legal threats, privacy issues, or escalation cases.
Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.
Do not fake metrics if the underlying issue list is incomplete.
## Output Rules
### Separate fact from judgment
The skill hard-codes Chinese output structures for the two default Linear comments without asking for or adapting to the user's preferred language. In a customer-support workflow, this can cause incorrect or unusable responses, create operator confusion, and increase the chance that staff post the wrong-language draft directly to customers or internal systems.
The analysis and reply patterns are written as fixed Chinese output templates, including required headings and response text, with no indication that another language may be used based on user preference. This can violate language/locale policy when applied to users who have not opted into Chinese-language handling.
No suspicious patterns detected.