Security audit
Security checks for vulnerabilities and agentic risk
This is a markdown-only Chinese test-case design skill, with some rough scoping and example-data issues but no hidden execution, exfiltration, or persistence behavior found.
Install this if you want Chinese-language help generating test-case tables. Before relying on it broadly, be aware that its Agent trigger is loose and its examples contain illustrative credentials/token text and a sandbox-style file-creation test; use test accounts, fake secrets, and controlled environments for any generated cases involving credentials, payments, permissions, files, or agent tools.
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
# 移动 Web 端测试检查清单
## 浏览器兼容性（12 项）
- [ ] iOS Safari 最新版本正常
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
# 移动 Web 端测试检查清单
## 浏览器兼容性（12 项）
- [ ] iOS Safari 最新版本正常
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
# 移动 Web 端测试检查清单
## 浏览器兼容性（12 项）
- [ ] iOS Safari 最新版本正常
Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.
# 移动 Web 端测试检查清单
## 浏览器兼容性（12 项）
- [ ] iOS Safari 最新版本正常
The skill description is very broad and can be triggered by many common testing-related requests without clearly stating when it should not apply. In an agentic environment, overbroad activation can cause the wrong skill to take control, leading to misrouting, instruction confusion, and unsafe reliance on irrelevant guidance.
The skill's natural-language instructions and invocation description are written to operate in Chinese, with no indication that users may choose another language. This can constitute a language/locale policy issue because it imposes a specific language without explicit opt-in or justification.
Using generic trigger terms like "Agent" or "智能体" is dangerous because these words may appear in many unrelated requests, causing accidental activation of the agent-testing workflow. This increases the chance of inappropriate file loading and response shaping, especially when other skills or general tasks mention agents only incidentally.
The instruction mapping table repeats the same ambiguous standalone trigger for agent testing, reinforcing the risk of false activation across unrelated contexts. Because this table appears to operationalize routing behavior, the ambiguity is more dangerous than a mere documentation issue and can systematically misclassify user intent.
This markdown file contains natural-language instructions and checklist items exclusively in Chinese, which can effectively force a specific language on users. Under the policy criteria, a language restriction should either provide user opt-in/choice or be clearly justified as region-specific.
This markdown file is entirely written in Chinese, beginning with the title 'AI Agent 测试', and nowhere indicates that the language is optional, user-selectable, or required for a specific region. Under the policy rule, forcing a specific language without opt-in is a natural-language locale violation.
The title and content define a single output format entirely in Chinese and state that all platforms share this same template. Because the file does not offer language choice or explain a justified region-specific requirement, it appears to force a specific language/locale without user opt-in.
The examples include realistic credentials, bearer tokens, and an Agent test that instructs creation of a local file without any warning that these values are illustrative only and must not be reused in real environments. In a test-design skill, users may copy examples verbatim into live systems or agent runs, which can normalize unsafe secret handling and unintended system-modification actions.
The entire skill file is written in Chinese and does not indicate that the user can choose another language or that the content is intentionally limited to a Chinese-language or region-specific audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The file title and all instructional content are written exclusively in Chinese, and there is no indication that the skill allows language choice or that Chinese is an explicitly required, justified locale. Under the policy rule, forcing a specific language without user opt-in can constitute a natural-language policy violation.
The document title and opening description are written as mandatory guidance for test case rules in Chinese, and the file provides no indication that language choice is optional or region-specific. Under the stated policy, forcing a specific language without user opt-in is a natural-language locale policy violation.
A default fallback to functional test case generation means the skill may activate even when no strong trigger is present. While not directly a code-execution issue, this weakens boundary control and can cause the system to apply this skill to vague or unrelated requests, reducing predictability and increasing prompt-routing errors.
This markdown file uses a single forced language for all instructions, beginning with the title and continuing throughout the checklist. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale limitation is explicitly justified.
The checklist title and content are entirely written in Chinese, and the file provides no indication that language selection is optional or that the checklist is intended only for a Chinese-specific context. Under the language/locale policy rule, forcing a specific language without user opt-in can be a natural-language policy violation.
This markdown file contains user-facing natural language content only in Chinese, starting from the title and continuing throughout the checklist. Under the policy rule for language/locale, forcing a single language without opt-in or documented justification can be a policy violation.
The entire skill file is presented in Chinese and does not state that the language is optional, user-selectable, or restricted to a justified Chinese-language context. Per SQP-3, forcing a specific language without user opt-in can be a natural-language policy violation.
This markdown file documents testing of user-information, phone, location, camera, album, Bluetooth, recording, storage, location, and payment capabilities, but it does not include any warning or note about handling personal data, permissions, or payment safety. Under the markdown-specific SQP-2 criteria, descriptions that involve privacy or system-impacting behaviors should disclose those impacts to users.
This markdown file uses a single forced language throughout, and there is no indication that users can choose another language or that the checklist is intentionally limited to a Chinese-speaking audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
This markdown file is natural-language content, and it presents all instructions and checklist items exclusively in Chinese. Under the policy, forcing a specific language without user opt-in can be a locale/language policy violation when no justification or alternative is provided.
The document title and all instructional content are written entirely in Chinese, with no indication that the user can choose another language or that the skill is region-specific. Under the policy criteria, a fixed language requirement without opt-in or documented justification is a natural-language policy concern.
This markdown file uses only Chinese-language instructions and headings throughout, beginning at L001, with no indication that the skill is region-specific or that users may choose another language. Under the language/locale policy rule, forcing a single language without opt-in can be a natural-language policy violation.
Detected: suspicious.exposed_secret_literal