Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward 1688 product-search integration that sends search terms to ClawEC using a user-provided API key.
Before installing, users should be comfortable sharing their search keywords and ClawEC API key with clawec.com, and should use a key intended only for this service. The skill does not show hidden persistence or destructive behavior.
The skill instructs use of shell-based execution (curl, bash scripts/search.sh) but does not declare any tool scope restrictions such as allowed-tools or permissions. That mismatch can let an agent invoke broader shell capabilities than are necessary, increasing the blast radius if the skill is triggered unexpectedly or its inputs are manipulated.
The description contains broad activation phrases covering many common product-research and sourcing requests, which can cause the skill to activate outside a narrowly intended context. Over-broad triggering is dangerous because it may expose API-backed network actions and data handling in situations where the user did not explicitly request this skill.
The script performs an external HTTP request to a third-party API using the user-supplied keyword and an Authorization bearer token from an environment variable. There is no confirmation prompt, user-facing notice, or explanatory comment/docstring warning that input data and credentials will be transmitted off-system.
The phrase '默认中文摘要' imposes a default language behavior in natural-language instructions without mentioning that the user may choose another language. This can conflict with language/locale policy expectations when no opt-in or alternative is offered.
The usage and error text are hard-coded in Chinese, which imposes a specific language on all users. There is no opt-in, fallback, or explanation that this skill is intended only for Chinese-speaking or region-specific use.
