Security audit
Security checks for vulnerabilities and agentic risk
This is a straightforward Baidu web search skill, with normal cautions around storing an API key and sending searches to Baidu.
Before installing, treat BAIDU_API_KEY as a secret: do not commit or share your OpenClaw config, restrict access to it, and rotate the key if exposed. Use this skill only for queries you are comfortable sending to Baidu's external service.
The skill requires environment access for BAIDU_API_KEY and performs network operations, but it does not declare an explicit tool scope such as permissions or allowed-tools. This weakens least-privilege controls and can let the skill execute with broader capabilities than reviewers or runners can easily validate, increasing the risk of secret exposure or unintended outbound access.
Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
Visit: **https://console.bce.baidu.com/ai-search/qianfan/ais/console/apiKey**
- Log in to your Baidu Cloud account
- Create an application or view existing API keys
- Copy your **API Key** (only API Key is needed)
### 2. Configure OpenClaw
The guide instructs users to place a live API key in a plaintext local configuration file but does not mention that the key is a sensitive secret, should be protected with restrictive file permissions, and must not be committed, shared, or logged. This can lead to accidental disclosure through backups, screenshots, shell history, support bundles, or source control, enabling unauthorized use of the Baidu service under the user's account.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
}
# 使用POST方法发送JSON数据
response = requests.post(url, json=requestBody, headers=headers)
response.raise_for_status()
results = response.json()
if "code" in results:
This code sends the request body, including the user-provided query, to an external HTTP endpoint. Although the script prints parse/debug output and errors, it does not clearly disclose to the user that their query content will be transmitted to Baidu, and no inline comment/docstring warns about that privacy-relevant behavior.
No suspicious patterns detected.