Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed TikTok Shop product-analysis API helper that sends product identifiers to ClawEC using the user's API key.
Install only if you intend to use ClawEC for TikTok Shop product analysis. Product IDs or links, region choices, log IDs, and your CLAWEC_API_KEY-backed requests will be sent to clawec.com, so avoid submitting sensitive or tracking-heavy URLs unless you are comfortable sharing them with that service.
声明的核心用途是“对 TikTok Shop 单品做商品分析”，预期行为应是接收商品标识并调用相应分析接口获取渠道分布、内容形式、流量结构或趋势等结果。而实际代码只是请求 product_analysis/search/logs 日志列表接口，参数也仅有分页用的 start、size，没有任何商品链接、商品 ID 或分析选项输入。这表明代码的主要功能是查看历史搜索/分析日志，而不是执行商品分析本身，因此属于实质性描述不符。
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")
The skill documents use of shell and environment-sourced credentials (bash, curl, CLAWEC_API_KEY) but does not declare an explicit tool/permission scope. That weakens least-privilege controls and makes it harder for a host agent or reviewer to constrain execution, especially if the skill is invoked automatically.
The invocation description includes broad triggers such as generic product analysis, link parsing, and command-like aliases, which can cause the skill to activate on loosely related user requests. Overbroad routing increases the chance of unintended external API calls and data sharing without a sufficiently specific user intent.
The skill instructs sending product links/IDs and an API credential to a third-party service but does not include a clear user-facing disclosure that data will leave the local environment. This creates privacy and consent risk, particularly if product URLs contain tracking parameters or if users do not expect external transmission.
The skill explicitly transmits user-provided product data and an authorization-backed request to an external domain. External transmission is expected for an API integration, but it is still security-relevant because it exposes user inputs and metadata to a third party and can incur unintended data leakage if invoked without consent.
| 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 $CLAWEC_API_KEY" \
-d '{"product":"1732414658666402537","region":"US","aiInterpret":true}'
The workflow says to '整理中文摘要' and the output guidance says '默认中文摘要', which imposes a specific language on users. The policy allows locale or language constraints only when users are given a choice or the constraint is clearly justified and documented.
This code performs a network request to an external API and includes an authorization credential from an environment variable, but the script provides no comment, prompt, or user-facing output disclosing that data will be transmitted. For code files, outbound network calls involving user or system data and credentials should have some visible warning unless clearly documented elsewhere.
This shell script performs an HTTP request and sends a bearer token from the CLAWEC_API_KEY environment variable in the Authorization header. The file contains no user-facing warning, confirmation, logging, or explanatory comment/docstring disclosing that it will use a sensitive credential in a network call.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
print(json.dumps(body, ensure_ascii=False))
' "$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 performs an outbound HTTP POST that transmits user-supplied product data and region information to an external service. Aside from the help text describing arguments, there is no runtime notice, confirmation, or warning that user input will be sent over the network.
This shell script presents its usage text and operational description entirely in Chinese, and later emits Chinese-only status/error messages as well. Because the file does not offer any user opt-in or alternative locale, it creates a natural-language locale policy concern under the rule for forced language selection.
The script returns JSON messages containing Chinese-only text for not-found and timeout conditions. These user-visible strings enforce a single language at runtime without presenting a choice or documenting a justified locale restriction.
The only natural-language user messages in the script are in Chinese, which imposes a specific language on all users without opt-in. The policy calls for flagging language or locale constraints unless the skill offers a choice or clearly documents a justified region-specific requirement.
The error message for a missing environment variable is hard-coded in Chinese: '请设置环境变量 CLAWEC_API_KEY'. This imposes a specific language in user-facing text without any opt-in, choice, or documented locale-specific justification.
The script's help output and error messaging are presented only in Chinese, with no option for the user to select another language or locale. This is a natural-language policy concern because it imposes a specific language choice rather than offering opt-in or documenting a justified locale restriction.
No suspicious patterns detected.