Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed ClawEC TikTok Shop product-analysis helper that sends user-provided product data to the ClawEC API using the user's API key.
Install only if you intend to use ClawEC's external API for TikTok Shop product analysis. Set CLAWEC_API_KEY as an environment variable rather than pasting it into chat, and be aware that product IDs or links, selected region, log IDs, and authenticated request metadata will be sent to clawec.com and may consume account credits.
声明的核心用途是对 TikTok Shop 单品进行分析，而提供的代码片段实际只是一个日志查询脚本：它接受分页参数并请求 product_analysis/search/logs 接口，返回的应是历史搜索/调用记录而非商品分析结果。这属于主目的不一致，并表现出未声明的日志访问能力。同时，声明中提到的商品分析具体维度和可选 AI 解读在代码里都没有体现，因此应判定为描述与行为不匹配。
Code enumerates, copies, or searches environment variables for secrets. Bulk environment access can collect credentials unrelated to the skill's stated purpose.
"aiInterpret": ai_interpret,
}
env = os.environ.copy()
search_sh = os.path.join(script_dir, "search.sh")
logs_sh = os.path.join(script_dir, "logs.sh")
detail_sh = os.path.join(script_dir, "log_detail.sh")
Without declared permissions the skill's intent is opaque and cannot be validated.
The skill sends user-supplied product identifiers or links, plus an API bearer token, to an external third-party service. Any external transmission creates a real data-boundary crossing risk: sensitive product URLs, analyst activity, and credentials may be exposed to the service, logs, or downstream processors, and the optional AI interpretation may further expand processing of submitted data.
| JP | 日本 |
curl -s -X POST "https://www.clawec.com/api/aigc/ec/tiktok/product_analysis/search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $CLAWEC_API_KEY" \
-d '{"product":"1732414658666402537","region":"US","aiInterpret":true}'
The workflow and output guidance instruct the skill to produce a Chinese summary by default, which imposes a language choice on the user. This is a natural-language policy issue because the file does not offer a user language choice or document a justified locale restriction.
This code performs a network request to an external API using a bearer token and includes the provided log identifier in the transmitted data. There is no confirmation prompt, logging, or inline notice warning the user that input and authenticated request metadata will be sent to a remote service.
This shell script reads a sensitive credential from the environment and sends an authenticated HTTP request, but it provides no comment, log message, or prompt informing the user that credentials will be used for a remote API call. For code files, accessing sensitive environment variables and transmitting data over the network should have some visible disclosure unless clearly warned elsewhere, which is not evident in this file.
The script's natural-language interface is presented in Chinese, including usage/help text and the environment-variable error message, with no option to select another language. This is a language-policy concern because the file forces a specific language without user opt-in or a stated regional justification.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
print(json.dumps(body, ensure_ascii=False))
' "$PRODUCT" "$REGION" "$AI_INTERPRET")
curl -s -X POST "https://www.clawec.com/api/aigc/ec/tiktok/product_analysis/search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d "$PAYLOAD"
This shell script posts user-provided product information to an external HTTPS endpoint using an Authorization bearer token, but outside of the help text there is no runtime disclosure, prompt, or visible notice that data will be transmitted off-system. For code files, outbound transmission of user or system data should have some form of user disclosure unless clearly warned or surfaced in the skill description.
The script's only user-facing messages are Chinese-only error/help strings, which forces a specific language for interaction. This can violate language/locale policy when no opt-in or alternative locale handling is provided.
The parameter-expansion error text is hardcoded in Chinese ("请设置环境变量 CLAWEC_API_KEY"), which imposes a specific language on all users. The policy allows locale constraints only when clearly documented and justified or when users are given a choice, neither of which is visible in this file.
The required API key error text is emitted only in Chinese, which continues the script's forced-language behavior. Even short operational messages should avoid imposing a single language unless the skill explicitly documents that locale restriction.
The script's user-facing help text is entirely in Chinese, including usage, description, and environment-variable explanations. This imposes a specific language on users without any visible opt-in, fallback, or documented justification for a locale-specific audience.
No suspicious patterns detected.