Trust Assessment
samsung-smart-tv received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 9 findings: 2 critical, 2 high, 2 medium, and 1 low severity. Key findings include Arbitrary command execution, File read + network send exfiltration, Dangerous call: subprocess.run().
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 40/100, indicating areas for improvement.
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 Findings9
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Python shell execution (os.system, subprocess) Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/regenrek/samsung-smartthings/scripts/setup_smartthings.py:117 | |
| CRITICAL | File read + network send exfiltration AI agent config/credential file access Remove access to sensitive files not required by the skill's stated purpose. SSH keys, cloud credentials, and browser data should never be read by skills unless explicitly part of their declared functionality. | Manifest | skills/regenrek/samsung-smartthings/SKILL.md:16 | |
| HIGH | Dangerous call: subprocess.run() Call to 'subprocess.run()' detected in function 'run_create'. This can execute arbitrary code. Avoid using dangerous functions like exec/eval/os.system. Use safer alternatives. | Static | skills/regenrek/samsung-smartthings/scripts/setup_smartthings.py:117 | |
| HIGH | Sensitive path access: AI agent config Access to AI agent config path detected: '~/.clawdbot/'. This may indicate credential theft. Verify that access to this sensitive path is justified and declared. | Static | skills/regenrek/samsung-smartthings/SKILL.md:16 | |
| MEDIUM | Suspicious import: urllib.request Import of 'urllib.request' detected. This module provides network or low-level system access. Verify this import is necessary. Network and system modules in skill code may indicate data exfiltration. | Static | skills/regenrek/samsung-smartthings/scripts/setup_smartthings.py:15 | |
| MEDIUM | SmartThings PAT exposed in process arguments The SmartThings Personal Access Token (PAT) is passed directly as a command-line argument (`--token`) to the SmartThings CLI. This makes the PAT visible in system process lists (e.g., 'ps aux') to other users or processes on the same system, which could lead to unauthorized access if the system is compromised. If the SmartThings CLI supports it, pass the PAT via an environment variable (e.g., `SMARTTHINGS_TOKEN=... smartthings apps:create`) or a secure input method instead of a command-line argument. Alternatively, ensure strict file permissions on the environment where this script runs. | LLM | scripts/setup_smartthings.py:120 | |
| LOW | OAuth authorization code exposed to httpbin.org The default OAuth redirect URI is set to `https://httpbin.org/get`. This means the authorization code, a temporary credential, will be sent to and displayed by httpbin.org. While the code is short-lived and immediately exchanged for tokens, its exposure to a third-party service, even a public one, is a minor data exfiltration risk. The user is given the option to override this. Advise users to configure a custom, secure redirect URI (e.g., a local server or a domain they control) for production use cases, or clearly explain the implications of using httpbin.org. | LLM | SKILL.md:22 | |
| INFO | Automatic package installation via npx -y The skill uses `npx -y @smartthings/cli` to automatically install and execute the SmartThings CLI. While `@smartthings/cli` is an official package, the `-y` flag bypasses user confirmation for installation, which could pose a supply chain risk if the package or its dependencies were compromised in the future. It also relies on the integrity of the npm registry. Consider removing the `-y` flag to require explicit user confirmation, or provide instructions for users to install the SmartThings CLI globally beforehand. Implement package integrity checks if possible. | LLM | scripts/setup_smartthings.py:40 | |
| INFO | Broad SmartThings API scopes requested The skill requests broad SmartThings API scopes (`r:devices:*` for read access to all devices and `x:devices:*` for execute commands on all devices). While these might be necessary for full functionality, they grant extensive control over all connected SmartThings devices. If the generated tokens are compromised, an attacker could control all devices. Review if the skill's functionality can be achieved with more granular scopes. If not, ensure robust security practices for handling and storing the generated OAuth tokens. | LLM | SKILL.md:20 |
Scan History
Embed Code
[](https://skillshield.io/report/b4bbaea2f8900651)
Powered by SkillShield