Security audit
Security checks for vulnerabilities and agentic risk
This skill is mostly a Chinese API documentation helper, but it promotes an external validation backend without clearly explaining when user documentation or API specs may be sent there.
Install only if you are comfortable with a Chinese-focused API documentation workflow and avoid using the external validation backend with private API specs, unreleased endpoints, secrets, customer data, or proprietary schemas unless the publisher clearly documents what is sent and obtains explicit consent.
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
| Pagination | 分页 | |
| Webhook | 回调通知 | or keep "Webhook" (widely used) |
| SDK | SDK | Don't translate |
| Access Token | Access Token | Don't translate |
| Timestamp | 时间戳 | |
| Deprecated | 已废弃 | |
| Required | 必填 | |
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.
| Pagination | 分页 | |
| Webhook | 回调通知 | or keep "Webhook" (widely used) |
| SDK | SDK | Don't translate |
| Access Token | Access Token | Don't translate |
| Timestamp | 时间戳 | |
| Deprecated | 已废弃 | |
| Required | 必填 | |
The skill promotes a real external API backend for documentation validation and provides a concrete base URL, but does not warn that user-supplied documentation, specs, or code-derived content may be transmitted off-platform. This creates a clear data exfiltration and confidentiality risk, especially if users validate internal APIs, unreleased endpoints, tokens, or proprietary schemas.
The skill advertises an executable shell script (scripts/validate.sh) and a real validation backend but declares no tool scope or permissions boundaries. In an agent environment, that can enable unexpected local command execution or make the agent appear able to run shell-based validation without explicit user awareness or policy constraints.
The trigger list is extremely broad (技术文档, 开发文档, API文档生成, etc.), which can cause the skill to activate for generic writing tasks outside its intended scope. Over-broad invocation increases the chance that unrelated or sensitive user content is pulled into a workflow that includes external validation or shell-based steps.
The description repeatedly positions the skill as the "ONLY" skill for Chinese API documentation generation and instructs use specifically for writing docs in Chinese. This is a natural-language locale constraint that does not offer user opt-in or an explicit choice of output language.
The documented ./scripts/validate.sh command encourages local shell execution without describing what it does, what files it reads, whether it makes network requests, or whether it modifies data. In an agent or developer workflow, undocumented scripts can become a vector for unintended command execution, network exfiltration, or destructive side effects.
The script's user-visible messages and guidance are entirely in Chinese, which imposes a specific language on all users. The file does not offer an opt-in language selection or explain that the skill is intentionally limited to a Chinese-speaking or region-specific audience.