Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward Google Trends lookup helper that sends user-provided keywords and an API key to Clawec's documented API.
Install only if you are comfortable sending search keywords and your Clawec API token to clawec.com. Avoid querying sensitive, proprietary, or personal terms unless your organization permits that data sharing.
代码的核心行为与声明总体一致：它确实调用 Clawec API 的 Google Trends 接口，并支持通过 region 参数按地区筛选。但声明中特别提到“支持多词对比”，而脚本只构造了包含单个 keyword 的请求体，没有多关键词数组、比较参数或多次请求逻辑，因此该能力与实际实现不符。除此之外，未发现额外未声明的敏感能力或资源访问。
The skill documents shell-based execution examples and references a local script, but it does not declare any tool scope or allowed-tools restrictions. In an agent environment, this can lead to over-broad execution capability, making it easier for the skill to invoke shell unexpectedly or beyond reviewer expectations.
The skill sends user-supplied keywords and an API key to an external third-party service. External transmission is expected for this skill’s purpose, but it still creates data exposure risk if users provide sensitive terms, and the skill does not prominently require user awareness/consent or data minimization before transmission.
单词 + 美国：
curl -s -X POST "https://www.clawec.com/api/aigc/ec/google_trend" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $CLAWEC_API_KEY" \
-d '{"keyword":"wireless earbuds","region":"US"}'
The instructions say the skill should '给出中文解读' and provide a '默认中文摘要', which imposes a specific language on outputs. This is a natural-language policy issue because the file does not offer the user a language choice or indicate opt-in for Chinese output.
This script performs an external network POST to a third-party API and includes an Authorization bearer token plus user-controlled content in the request body. In the context of an agent skill, external transmission is expected for functionality, but it still creates a real confidentiality and supply-chain risk because sensitive queries may leave the local environment and depend on the security of an external service.
print(json.dumps(body))
' "$KEYWORD" "$REGION")
curl -s -X POST "https://www.clawec.com/api/aigc/ec/google_trend" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d "$PAYLOAD"
The script transmits both user-supplied query data and a bearer API credential to an external third-party endpoint without any inline disclosure, consent prompt, or trust boundary explanation. In an agent/skill context, this is security-relevant because users may not realize their inputs are being sent off-platform and operators may unintentionally expose sensitive search terms to a remote service.
This markdown file presents all user-facing schema documentation in Chinese and does not indicate that users may choose another language. Under the policy for natural-language violations, forcing a specific language without user opt-in can be a locale/language policy issue.
The usage and environment-variable error strings are presented only in Chinese, which imposes a specific language on users without opt-in or justification. This can violate language/locale policy where skills should not force a language unexpectedly.
No suspicious patterns detected.