Trust Assessment
baidu-scholar-search-skill received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Command Injection via Unquoted User Input in `curl` URL.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Command Injection via Unquoted User Input in `curl` URL The `WD`, `pageNum`, and `enable_abstract` variables, which are derived directly from untrusted user input (`$1`, `$2`, `$3`), are interpolated into the `curl` command's URL string without proper shell quoting or URL encoding. This allows an attacker to inject shell metacharacters (e.g., `;`, `|`, `$(...)`) into the arguments, leading to arbitrary command execution on the host system. For example, providing `WD="; rm -rf /; echo "` could execute `rm -rf /`. To prevent command injection, use `curl`'s `-G` (for GET requests) and `--data-urlencode` options for each parameter. This ensures that `curl` handles the URL encoding of the parameter values safely and prevents shell interpretation of user input. Modified snippet: ```bash curl -s -X GET \ -H "Authorization: Bearer $BAIDU_API_KEY" \ -H "X-Appbuilder-From: openclaw" \ -G \ --data-urlencode "wd=$WD" \ --data-urlencode "pageNum=$pageNum" \ --data-urlencode "enable_abstract=$enable_abstract" \ "https://qianfan.baidubce.com/v2/tools/baidu_scholar/search" ``` | LLM | baidu_scholar_search.sh:30 |
Scan History
Embed Code
[](https://skillshield.io/report/e56a8d4641e1766b)
Powered by SkillShield