Security audit
Security checks for vulnerabilities and agentic risk
This skill is a straightforward ClawEC API helper for Ozon keyword ranking research, with expected external API use and no evidence of hidden persistence or unrelated data access.
Install this only if you are comfortable sending Ozon keyword research queries and your ClawEC API key to www.clawec.com. Use the CLAWEC_API_KEY environment variable rather than hardcoding secrets, and review the curl/script examples before running them.
The skill documents shell-based execution paths (curl and bash scripts/query.sh) but does not declare any tool scope or allowed-tools restrictions. This can cause an agent runtime to overgrant capabilities or invoke shell access implicitly, increasing the risk of unintended command execution and making review and sandboxing harder.
The skill sends user-supplied query parameters and an API bearer token to an external third-party service. Even though external API use is the intended function, it still creates a real data-transmission boundary: sensitive inputs, business research terms, and credentials may be exposed to that service or to logs if not carefully handled.
curl -s -X POST "https://www.clawec.com/api/aigc/ec/ozon/data/keyword/hot-ranking" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $CLAWEC_API_KEY" \
-d '{"period":"WEEK","pageNo":1,"pageSize":15,"sortField":"SEARCH_INDEX","sortDirection":"DESC"}'
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
print(json.dumps(body, ensure_ascii=False))
' "$PERIOD" "$PAGE_NO" "$PAGE_SIZE" "$SORT_FIELD" "$SORT_DIRECTION" "$UPDATE_PERIOD" "$FILTERS_JSON")
curl -s -X POST "https://www.clawec.com/api/aigc/ec/ozon/data/keyword/hot-ranking" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d "$PAYLOAD"
This code performs an outbound HTTP POST to a third-party domain and includes user-supplied payload data plus a bearer token, but the script provides no confirmation prompt, logging, or inline warning to disclose that data will be transmitted externally. For a code file, this matches the missing user warning criterion for network calls that transmit user or system data.
The markdown explicitly states '默认中文报告', which imposes a language choice in the skill's output behavior. Under the policy, locale or language constraints should either be optional, user-selected, or clearly justified as region-specific; this file does not provide such an opt-in.
The guidance says to display results using the Chinese keyword first, with Russian only optionally appended. This imposes a language preference in the skill's behavior without indicating user choice or opt-in, which can violate locale/language policy expectations.
The usage and error messages are presented only in Chinese, which imposes a specific language on users without any opt-in or stated regional justification. This is a natural-language policy concern because the file contains user-facing text that does not provide locale choice.