Security audit
Security checks for vulnerabilities and agentic risk
This skill is a local Chinese-language LinkedIn outreach text generator and does not send messages, access accounts, or persist data.
Install this if you want local drafting help for Chinese LinkedIn sales outreach. Review generated messages before use, avoid entering unnecessary personal or sensitive profile details, and confirm that the final outreach complies with LinkedIn and applicable marketing rules.
The trigger phrases are broad enough to match many ordinary LinkedIn-related requests, which can cause the skill to activate outside its intended scope. In an agent setting, this can lead to prompt-routing confusion, unintended message generation, and misuse of user or profile context for outreach content when the user did not explicitly request this skill.
Repeating ambiguous invocation terms without precise activation rules increases the chance that the orchestrator or agent will select this skill for unrelated LinkedIn tasks. That can produce unintended outbound-sales content, incorrect automation behavior, or disclosure of provided profile details into generated outreach text in contexts where the user expected general advice instead.
This code is a multilingual-context outreach generator, but its natural-language interface and generated message content are hard-coded primarily in Chinese, with no option for the user to select another language or locale. That creates a language/locale policy concern because the skill imposes a specific language by default rather than offering explicit user choice.
Natural-language content in the manifest forces a specific language presentation, and the file does not indicate that the user can choose another language. Under the policy, locale or language constraints should be optional or clearly justified when they are imposed.
No suspicious patterns detected.
