Security audit
Security checks for vulnerabilities and agentic risk
The skill is a Markdown-only decision helper with disclosed, bounded behavior and no evidence of hidden execution, data access, persistence, or exfiltration.
Install this only if you want a Chinese-language meta-decision helper that nudges the agent to pick one next action during branching, costly, or stalled work. Review the 'degrade_continue' behavior if you prefer agents to pause for confirmation before irreversible or public actions.
The manifest description is written as a Chinese-only instruction for the skill and presents the behavior as a general-purpose internal skill, without offering any language or locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
This markdown file contains all substantive instructions and examples in Chinese, with no indication that users may choose another language. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy concern.
This markdown file contains user-facing natural-language guidance almost entirely in Chinese, including headings, context, and trigger-exclusion examples. The file does not indicate that Chinese is optional, user-selected, or required for a specific region, which can violate a language/locale policy requiring user choice or explicit justification.
The reference content is entirely written in Chinese and does not offer any language choice, opt-in, or justification for a locale-specific restriction. Under the policy criteria, forcing a specific language without user choice is a natural-language policy violation.
The document presents all operational trigger guidance exclusively in Chinese, starting with the heading at L03 and continuing throughout the file. Because no alternative language option, opt-in, or justification for a Chinese-only locale is provided, this is a natural-language locale policy issue under the rule.
No suspicious patterns detected.
