Trust Assessment
x-trends received a trust score of 35/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 5 findings: 2 critical, 1 high, 2 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Unverified Script Execution for Agent Installation, Unverified Executable Download for Agent Installation.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 41/100, indicating areas for improvement.
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 Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Network egress to untrusted endpoints URL pointing to known exfiltration/webhook service Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/hightower6eu/x-trends-kzcxt/SKILL.md:10 | |
| CRITICAL | Unverified Script Execution for Agent Installation The skill instructs users to copy and paste an installation script from `glot.io` (a general-purpose code snippet hosting service) into their terminal for macOS `openclaw-agent` setup. This is a severe supply chain risk as the content of the script is untrusted, unverified, and could change at any time, potentially leading to arbitrary command execution on the user's system. Provide a secure, verified method for installing `openclaw-agent` on macOS, such as a signed package, a script with a checksum, or instructions to build from a trusted source. Avoid using general-purpose snippet hosting services for executable code. | LLM | SKILL.md:10 | |
| HIGH | Unverified Executable Download for Agent Installation The skill instructs users to download `openclaw-agent.zip` directly from a GitHub release URL using the `latest` tag. This method lacks checksum verification, meaning a malicious actor could replace the `latest` release with a tampered executable without the user's knowledge. Provide a specific versioned download link along with a cryptographic hash (e.g., SHA256) for users to verify the integrity of the downloaded file. | LLM | SKILL.md:8 | |
| MEDIUM | Unpinned `twurl` Gem Installation The skill's manifest and setup instructions recommend installing the `twurl` gem without specifying a version. This can lead to unexpected behavior, breaking changes, or even the installation of a malicious version if a supply chain attack targets the `twurl` gem. Pin the `twurl` gem to a specific, known-good version (e.g., `gem install twurl -v 0.4.2`). | LLM | SKILL.md:20 | |
| MEDIUM | API Keys Exposed in Command Line Example The setup instructions provide an example command `twurl authorize --consumer-key YOUR_API_KEY --consumer-secret YOUR_API_SECRET` which, if followed literally, would expose the user's API key and secret directly in the shell history and process list. While `twurl` typically handles authorization interactively and securely, this example encourages an insecure practice. Modify the instruction to guide users towards the secure, interactive authorization flow of `twurl`, e.g., "Run `twurl authorize` and follow the prompts to securely enter your consumer key and secret." | LLM | SKILL.md:24 |
Scan History
Embed Code
[](https://skillshield.io/report/1dfafae227facb42)
Powered by SkillShield