Trust Assessment
midea_ac received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via unescaped arguments in skill execution.
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 12, 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 unescaped arguments in skill execution The `SKILL.md` defines commands like `scripts/midea_ac.py <room-name> on` where `<room-name>` is a user-controlled input. If the orchestrating LLM constructs this shell command string by directly interpolating user-provided values without proper shell escaping, a malicious user could inject arbitrary shell commands. For example, providing `<room-name>` as `bedroom; rm -rf /` could lead to execution of `rm -rf /` if the orchestrator uses `shell=True` or similar unsafe execution methods. While the Python script `midea_ac.py` uses `argparse` which mitigates injection *within* the script's argument parsing, the initial shell execution context remains vulnerable. The orchestrating LLM should execute shell commands by passing arguments as a list (e.g., `subprocess.run(['python', 'scripts/midea_ac.py', room_name, command])`) instead of a single string, or ensure all user-controlled inputs are rigorously shell-escaped before command string construction. The skill developer should also consider validating or sanitizing `room-name` more strictly if it's meant to be a fixed set of values. | LLM | SKILL.md:42 |
Scan History
Embed Code
[](https://skillshield.io/report/17125b7bf81ee973)
Powered by SkillShield