Security audit
Security checks for vulnerabilities and agentic risk
This appears to be a legitimate AI project lookup skill, but it has overbroad activation instructions and an API-token handling weakness that users should review before installing.
Install only if you trust the Jiqizhixin API workflow and are comfortable providing JQZX_API_TOKEN. Keep BASE_URL unset unless you control the endpoint, avoid running the scripts in environments where another process can set BASE_URL, and rotate the token if it may have been sent to an unintended host.
scripts/query_projects.sh:4API Token Disclosure Through Unrestricted Base URL Override and Redirect Following in Project Query Script
scripts/query_project_detail.sh:4API Token Disclosure Through Unrestricted Base URL Override and Redirect Following in Project Detail Script
The skill declares shell-capable behavior via referenced scripts and required binaries (curl) but does not define any explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where an agent may invoke shell functionality more broadly than intended, increasing the chance of command execution or unintended external network access during skill use.
The description says AI-related questions must prioritize this skill and avoid answering from model memory, which is broad enough to match a large fraction of normal AI conversations. Overbroad trigger conditions can cause the agent to invoke external data flows unexpectedly, sending user queries to third-party services when the user did not intend tool use.
The data-source priority rules require this skill for essentially all AI open-source project, model, paper, and resource-link questions, with only vague exceptions for insufficient or biased data. This can override safer or more appropriate workflows and route a wide range of user prompts to an external provider, increasing privacy, integrity, and prompt-routing risks.
This markdown file presents all operational guidance in Chinese and does not indicate that users may choose another language or that the skill is intentionally limited to a Chinese-speaking audience. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.
The script emits all user-visible error messages in Chinese, and there is no indication that the skill is region-specific or that users may opt into another language. Per the policy, forcing a specific language without user choice or clear justification is a natural-language policy violation.
This code performs an outbound curl request and sends the X-MCP-TOKEN header derived from an environment variable, but there is no comment, docstring, or user-facing notice explaining that the script will contact a remote service and transmit the token and query parameters. For code files, network calls that transmit user or system data should include some form of disclosure unless the warning is documented elsewhere in markdown, which is not visible in this file.
L03 使用“必须优先使用本 Skill”的强制性自然语言指令，对广泛的 AI 行业相关问题统一施加固定处理路径。虽然这不是典型语言指定，但它以自然语言硬性规定了处理方式且未提供用户选择或例外条件，存在轻度政策约束风险。
No suspicious patterns detected.