Security audit
Security checks for vulnerabilities and agentic risk
The skill is a coherent legal-search integration, but it can automatically send potentially sensitive legal questions to a third-party MCP service without clear confirmation or confidentiality guardrails.
Install only if you are comfortable routing legal research queries to aixllaw's remote MCP service. Avoid sending confidential case facts, privileged attorney-client material, trade secrets, or personal data unless you have reviewed the provider's terms and data handling. If you use an API key, store it only in the intended MCP configuration and review that configuration periodically.
Remote code is downloaded and executed. This bypasses code review and could introduce malicious code.
echo "Session: $SESSION_ID"
# Step 2: 执行法律检索
curl -s https://mcp.aixllaw.com/mcp \
-X POST \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
The skill enables implicit invocation for a remote MCP tool without any trigger constraints, exclusions, or user-confirmation guardrails. In a legal-research context, this can cause the agent to automatically send user queries or surrounding context to a third-party service when legal topics are detected, increasing the risk of unintended data disclosure and unreviewed tool use.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
# 验证服务在线（免登录模式无需 token，内置免费额度，配置后即可直接使用）
# 说明：此请求并非完整 MCP 协议调用，返回 400/406 等错误状态码即代表服务在线可达，属正常现象
curl -s https://mcp.aixllaw.com/mcp \
-X POST \
-H "Content-Type: application/json" \
-d '{}'
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
echo "Session: $SESSION_ID"
# Step 2: 执行法律检索
curl -s https://mcp.aixllaw.com/mcp \
-X POST \
-H "Content-Type: application/json" \
-H "Accept: application/json, text/event-stream" \
This markdown file presents all operational guidance, examples, and warnings exclusively in Chinese, and does not indicate that the user can choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy violation.
The file mixes a Chinese-facing interface with an English-only default prompt, but does not offer a language choice or explain the locale behavior. This may force a specific language mode without user opt-in, which fits the language/locale policy concern.
This file's natural-language instructions, examples, and expected user prompts are all Chinese-only, with no indication that users may choose another language or locale. Under the policy-violation category, forcing a specific language without user opt-in can be a language/locale policy issue.
Detected: suspicious.exposed_secret_literal