Trust Assessment
volcengine-web-search 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 Potential Shell Command Injection via User-Controlled Query.
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 13, 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 | Potential Shell Command Injection via User-Controlled Query The skill's instructions explicitly guide the LLM to execute a shell command `python scripts/web_search.py "query"` where the `query` is derived from user input. If the LLM constructs this command string by directly concatenating the user's `query` without proper shell escaping, a malicious user could inject arbitrary shell commands. For example, a `query` like `"; rm -rf /tmp/*; echo "` could lead to the execution of `rm -rf /tmp/*` on the host system. The LLM should be instructed to execute the script using a safe method that avoids shell interpretation of arguments. This typically involves passing arguments as a list to a subprocess function (e.g., `subprocess.run(["python", "scripts/web_search.py", query])`) rather than constructing a single shell string. If shell execution is strictly necessary, the user-provided `query` must be thoroughly escaped using a function like `shlex.quote()` before being embedded in the command string. | LLM | SKILL.md:9 |
Scan History
Embed Code
[](https://skillshield.io/report/9297b29f547032f3)
Powered by SkillShield