Security audit
Security checks for vulnerabilities and agentic risk
This skill is coherent for sales outreach, but it can drive public posting and customer outreach with broad triggers and no clear required approval step before outbound actions.
Review this skill carefully before installing. Use it in draft-first mode where possible, require explicit approval before every post or message, verify target platforms and accounts, and avoid using it for bulk outreach or personal/contact data unless you have a lawful basis and platform-compliant process.
The description promotes one-click multi-platform publishing and end-to-end automation, but does not clearly warn that the skill may perform outbound posting actions on external platforms. Users may interpret this as a content assistance tool rather than one capable of taking externally visible actions, creating risk of unauthorized or surprising posts under connected accounts.
The trigger list uses broad, common sales phrases such as 销售线索, 获客, and 开发信 that could match ordinary user requests and invoke the skill unexpectedly. Because this skill can drive research, content generation, and downstream publishing actions, accidental invocation increases the chance of unintended data gathering or outreach workflows being initiated.
The workflow explicitly includes publication steps across 小红书, 微信文章, and LinkedIn, but nowhere requires an explicit confirmation step immediately before posting. In context, this is more dangerous because the skill is designed for scaled outreach and lead generation, so unintended execution could result in spam-like behavior, reputational damage, or unauthorized communications from the user's accounts.
All natural-language descriptions, triggers, stage names, and examples are presented only in Chinese, with no indication that users may interact in another language or opt into this locale. Under the stated policy, a language-specific constraint should either be optional for the user or clearly justified as region-specific.
The trigger list is broad and generic for common sales activities such as lead generation, outreach, and customer contact. This increases the chance of unintentional activation in unrelated conversations, causing the workflow to initiate web research, profiling, and content-generation actions without sufficiently specific user intent.
No suspicious patterns detected.
