Security audit
Security checks for vulnerabilities and agentic risk
This is a prompt-only CI/CD log troubleshooting skill that generates diagnostic reports and suggested commands without executing them or adding persistence.
Before installing, confirm you are comfortable with a Chinese-language CI/CD troubleshooting workflow. Paste only the relevant failure-log excerpt, redact secrets first, and review any suggested repair or rollback command before running it in production.
The README presents the skill name, description, and usage instructions only in Chinese. Per the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is explicitly documented and justified.
The manifest description is entirely in Chinese and presents the skill as producing reports and instructions in that language, with no indication that users may choose another language. The policy for this audit flags language or locale constraints when they are imposed without explicit opt-in or documented justification.
This JSON file is a manifest-like file, so SQP-3 applies to its natural-language content. The expected output strings and validation rules require Chinese output phrases such as "CI/CD 故障诊断报告" and other Chinese-language content, but there is no indication that language selection is optional or justified by a region-specific purpose.
The expected output for this case is specified with Chinese terms like "超时", "模块缺失", and "预防 Checklist", which effectively constrains the skill's language behavior. Because no user choice or policy justification is present in the file, this is a natural-language locale policy concern.
The manifest description is written entirely in Chinese and presents the skill as a Chinese-language assistant without offering any user opt-in or multilingual option. That can violate language/locale policy when a skill implicitly forces a specific language for all users without documented justification.
This JSON manifest describes the skill's purpose in broad natural language but does not define any explicit trigger phrases, invocation boundaries, or negative examples. In manifest files, that lack of specificity can make it unclear when the skill should activate versus when related CI/CD troubleshooting requests should not invoke it.
No suspicious patterns detected.
