Trust Assessment
homeassistant-assist received a trust score of 88/100, 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 User Input in `curl` command.
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 | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via User Input in `curl` command The skill's description illustrates its functionality using a `curl` command where user input (`USER REQUEST HERE`) is directly embedded into the JSON payload within a single-quoted string for the `-d` argument. If the skill's implementation constructs this `curl` command using shell execution (e.g., `subprocess.run(..., shell=True)` or `os.system()`), a malicious user could inject arbitrary shell commands by crafting `USER REQUEST HERE` to break out of the JSON string and execute shell commands. For example, input like `", "language": "en"}' && echo pwned #` could lead to command execution. Avoid constructing shell commands with user-controlled input. Instead, use a dedicated HTTP client library (e.g., `requests` in Python) to make API calls, which handles JSON serialization and HTTP requests safely without involving the shell. If `curl` must be used, ensure all user input is strictly validated and properly escaped for both JSON and shell contexts before being included in the command string. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/d83e4ebf3a6aca83)
Powered by SkillShield