Trust Assessment
amap received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via Unsanitized User Input in `curl` commands.
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 | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via Unsanitized User Input in `curl` commands The skill's documentation demonstrates constructing `curl` commands by directly embedding user-provided input (e.g., `[关键词]`, `[城市adcode]`, `[地址]`) into the command string. If the AI agent directly interpolates these user inputs into a shell command without proper sanitization or quoting, an attacker could inject arbitrary shell commands by crafting malicious input (e.g., `foo; rm -rf /`). This could lead to arbitrary code execution on the host system where the skill is run, as the manifest explicitly allows `curl` execution. The AI agent or the skill execution environment must ensure that all user-provided inputs used in shell commands are properly sanitized, URL-encoded, or quoted to prevent shell metacharacters from being interpreted as commands. For `curl` commands, robust URL encoding of parameters is crucial, and the entire command string should be passed to the shell in a way that prevents arbitrary command execution (e.g., using `subprocess.run` with `shell=False` and passing arguments as a list, or robust shell escaping). | LLM | SKILL.md:40 |
Scan History
Embed Code
[](https://skillshield.io/report/864b83f643ad34ae)
Powered by SkillShield