Security audit
Security checks for vulnerabilities and agentic risk
This skill is a Chinese API documentation helper with a disclosed validation backend, and I found no hidden credential access, persistence, or destructive behavior.
Install only if you want Chinese API documentation behavior. Avoid sending confidential internal specs, endpoint details, or unreleased API documentation to the external validation backend unless you are comfortable with that service processing the content.
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 advertises and instructs use of an executable shell script and a remote validation backend, but it declares no tool scope or execution constraints. That creates a capability mismatch where an agent may invoke shell behavior or networked validation without explicit permission boundaries, increasing the risk of unintended command execution or exfiltration when processing untrusted API specs or documentation.
The trigger list is excessively broad and overlaps with ordinary documentation and technical-writing requests, making accidental auto-invocation more likely. When combined with shell and backend validation features, overly broad activation expands the number of contexts in which the skill could gain access to sensitive code, specs, or internal endpoint descriptions.
The instruction states that the skill specializes in Chinese API documentation and later repeatedly directs generation of Chinese docs, but it does not present this as an opt-in language choice within the skill behavior. Under the policy, forcing a specific language without user opt-in is a natural-language locale violation unless clearly justified as region-specific.
The script's user-facing messages are entirely in Chinese, including the title and status/best-practice guidance. This imposes a specific language on users without offering an opt-in, fallback, or documenting a locale-specific purpose.
No suspicious patterns detected.