Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed ClawHub skill-search helper with a simple search wrapper and no hidden persistence, credential access, or destructive behavior.
Before installing skills recommended by this helper, review `clawhub inspect <skill-name>` output and confirm you trust the publisher; the helper itself is narrowly scoped, but installed third-party skills may have their own permissions and risks.
The trigger phrase examples are broad enough to match ordinary requests about finding tools or getting help, which can cause the skill to activate outside its intended niche. In a skill whose purpose is to search for and install other skills, overbroad activation increases the chance of unsolicited marketplace guidance or installation suggestions in unrelated conversations.
The activation conditions describe broad user intents like '有没有 skill 可以...' without requiring strong scope checks, so the agent may invoke this skill for ambiguous requests that merely resemble product discovery. Because the skill can lead directly from search to inspection and installation commands, ambiguous invocation increases the risk of steering users toward unintended third-party content or package installation flows.
The manifest identifies the skill as a Chinese-specific variant ("skill-finder-cn") and explicitly advertises "中文优化" without indicating that language selection is optional or user-controlled. This can violate language/locale policy when the skill behavior is constrained to a specific locale without explicit opt-in or documented justification.
The trigger set includes very generic phrases such as "有什么技能", "find skill", and "search skill", which can match ordinary conversation and cause the skill to activate unexpectedly. In a skill that influences discovery and installation of other skills, unintended invocation can steer users toward actions they did not explicitly request and create an unnecessary prompt-surface for downstream abuse or confusion.
The package name and description explicitly label the skill as "CN" and include Chinese-only localization cues, but the file provides no indication that users can opt into this locale or that the restriction is region-specific and justified. This can indicate a natural-language locale policy issue when a skill appears to enforce a specific language or locale by default.
The script contains user-facing text exclusively in Chinese in the comment and usage output, which imposes a specific language/locale without user opt-in. The policy allows locale constraints only when they are explicitly documented and justified, which is not present here.
No suspicious patterns detected.
