Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward Shopee product-search integration that sends search terms to Clawec with a user-provided API key, with no evidence of hidden persistence, destructive behavior, or unrelated data access.
Install this only if you are comfortable using Clawec for Shopee research: your search keyword, selected region, and Clawec API key will be sent to clawec.com. Use a dedicated API key if possible, avoid entering sensitive search text, and review Clawec's account and API terms before relying on the results.
The skill documents shell-based execution (curl and bash scripts/search.sh) but does not declare any permissions or allowed-tools scope. This creates an authorization gap where an agent may invoke shell capabilities implicitly, making external network access and script execution less transparent and harder to constrain or review.
The skill instructs the agent to send user-supplied search terms and an API bearer token to an external third-party endpoint. External transmission is expected for this skill’s purpose, but it is still a real security/privacy boundary because user input and credentials leave the local environment and are processed by an outside service.
curl -s -X POST "https://www.clawec.com/api/aigc/ec/shopee_search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $CLAWEC_API_KEY" \
-d '{"keyword":"蓝牙耳机","region":"PH"}'
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
print(json.dumps(body))
' "$KEYWORD" "$REGION")
curl -s -X POST "https://www.clawec.com/api/aigc/ec/shopee_search" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d "$PAYLOAD"
This shell script sends the user-supplied keyword and optional region to an external HTTPS API and authenticates with a sensitive environment variable, but the file provides no comment, echo/log message, or confirmation indicating that data will be transmitted off-host. For code files, outbound network transmission and use of credentials should have some visible disclosure unless clearly documented elsewhere, which is not present in this file.
The markdown states '默认中文摘要', which imposes a specific language preference in the skill's behavior. Under the policy, language constraints should either be user-selected or clearly justified; this file does not present Chinese as an opt-in choice.
This markdown file contains user-facing documentation only in Chinese, which can amount to a language-policy issue if users are not given a choice or informed that the skill is intentionally limited to that locale. The file does not indicate any opt-in, alternative language, or explicit justification for the language restriction.
The usage and error strings are written only in Chinese, which imposes a specific language on all users of the skill. The file does not offer a language choice, fallback, or any justification that the skill is intended only for a Chinese-language or region-specific audience.