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 4 findings: 2 critical, 1 high, 0 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Unverified binary installation with root privileges (macOS), Unverified executable download and execution (Windows).
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 53/100, 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 Findings4
| 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/jordanprater/xtrends/SKILL.md:10 | |
| CRITICAL | Unverified binary installation with root privileges (macOS) The skill requires 'openclawcli' to function. The macOS installation instructions direct users to visit an external page (glot.io) which contains a script that downloads and installs an arbitrary binary from a personal GitHub repository (Ddoy233/openclawcli) into '/usr/local/bin' using 'sudo'. This allows for arbitrary code execution on the host system with root privileges if the 'openclawcli' binary is malicious or compromised. This is a severe supply chain risk. Remove the mandatory dependency on 'openclawcli' or provide a secure, verified, and auditable installation method. If 'openclawcli' is essential, its source code should be thoroughly reviewed, and it should be distributed through trusted package managers or verified channels. Avoid instructing users to execute 'sudo' commands for installing third-party binaries from unverified sources. | LLM | SKILL.md:9 | |
| HIGH | Unverified executable download and execution (Windows) The skill requires 'openclawcli' to function. The Windows installation instructions direct users to download a password-protected '.zip' file from a personal GitHub repository (Ddoy233/openclawcli), extract it, and run the executable. This allows for arbitrary code execution on the host system if the 'openclawcli' executable is malicious or compromised. The use of a password-protected zip for an executable from an unverified source is also suspicious. Remove the mandatory dependency on 'openclawcli' or provide a secure, verified, and auditable installation method. If 'openclawcli' is essential, its source code should be thoroughly reviewed, and it should be distributed through trusted channels. Avoid instructing users to download and run executables from unverified sources. | LLM | SKILL.md:7 | |
| LOW | Unpinned 'twurl' gem dependency The skill instructs 'gem install twurl' without specifying a version. This command installs the latest available version of the 'twurl' gem. While 'twurl' is a legitimate tool, unpinned dependencies can introduce supply chain risks if a malicious or vulnerable version is published to the gem repository, potentially leading to unexpected behavior or security flaws. Specify a version for the 'twurl' gem (e.g., 'gem install twurl:1.x.x') or use a Gemfile with a lock file to ensure deterministic and secure installations, mitigating risks from future malicious or vulnerable releases. | LLM | SKILL.md:19 |
Scan History
Embed Code
[](https://skillshield.io/report/2109cda2fce96288)
Powered by SkillShield