Trust Assessment
say-xiaoai 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 Unquoted variable in shell script leads to command injection.
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 | Unquoted variable in shell script leads to command injection The `say_xiaoai.sh` script executes the `say` command with an unquoted variable `$1`. This variable directly receives user-controlled input from the `query` parameter. An attacker can inject shell metacharacters (e.g., `;`, `&&`, `||`, `$(...)`) into the `query` parameter to execute arbitrary commands on the host system. Always quote variables that contain user-controlled input when used in shell commands to prevent command injection. Change `say $1` to `say "$1"` in `say_xiaoai.sh`. | LLM | say_xiaoai.sh:4 |
Scan History
Embed Code
[](https://skillshield.io/report/654bb898d0d96a74)
Powered by SkillShield