Security audit
Security checks for vulnerabilities and agentic risk
This skill is a local code documentation generator with disclosed optional Feishu export and no evidence of hidden execution, persistence, or data exfiltration.
Install only if you want an agent to inspect selected source files and generate API documentation. Review generated output for internal endpoints, schemas, comments, or secrets before saving broadly or sending it to Feishu.
The declared behavior says the skill generates API/technical docs and supports Feishu output, but the content indicates mismatches between what is promised and what is actually implemented. Such mismatches are dangerous because users may authorize the skill under false assumptions, leading to unexpected processing, data handling, or downstream sharing behavior.
Referenced artifact was not completely inspected
python3 scripts/extract_api.py app/routes.py --format markdown
Referenced artifact was not completely inspected
python3 scripts/extract_api.py app/routes.py --format markdown
Referenced artifact was not completely inspected
python3 scripts/extract_api.py app/routes.py --format markdown
Referenced artifact was not completely inspected
python3 scripts/extract_api.py app/routes.py --format markdown
The skill instructs reading source files and writing generated documentation to local files, but it declares no explicit tool scope such as permissions or allowed-tools. This increases the risk of overbroad file access and unintended writes because the runtime has no documented boundary for what paths or tools the skill should be allowed to use.
The description advertises Chinese document templates, and the parameter section states “--chinese：使用中文模板（默认中文）”, making Chinese the default output behavior. This is a language/locale constraint presented without a clear user opt-in or explicit alternative default, which may violate language-choice policy expectations.
The trigger phrases are broad enough to match common requests like general writing or document generation, which can cause the skill to activate outside its intended narrow context. Over-triggering is risky because it may lead the agent to read source code or prepare exports when the user only wanted generic assistance, increasing accidental data exposure and unauthorized file handling.
The skill describes writing generated content to Feishu cloud documents and local files without an explicit warning that source-derived content may be disclosed to external systems or persisted on disk. In this context, generated documentation may include sensitive code details, endpoints, internal schemas, or secrets accidentally extracted from comments, making silent export materially dangerous.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
| 版本 | v1.0.0 |
| 更新日期 | {date} |
| 维护团队 | {team} |
| Base URL | `https://api.example.com/v1` |
## 快速开始
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
请求示例
curl -X {METHOD} "{base_url}{path}" \
-H "Authorization: Bearer YOUR_TOKEN" \
-H "Content-Type: application/json" \
-d '{request_body}'
This code makes Chinese the default output language by setting --chinese to true by default and computing chinese = not args.english, so users receive Chinese output unless they explicitly override it. That is a natural-language locale policy concern because the skill forces a specific language choice rather than offering neutral default behavior or explicit opt-in.
No suspicious patterns detected.