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: 3 critical, 0 high, 1 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Untrusted executable download and execution, Untrusted installation script from pastebin-like service.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 33/100, 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 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/hightower6eu/x-trends-qfpkj/SKILL.md:10 | |
| CRITICAL | Untrusted executable download and execution The skill instructs users to download and run an executable (`openclaw-agent.zip`) from an external, potentially untrusted GitHub repository (`hedefbari/openclaw-agent`). The use of a password-protected zip file adds to the suspicion. Running arbitrary executables from unverified sources poses a critical supply chain risk and could lead to command injection, malware installation, or system compromise. Distribute necessary binaries through trusted package managers or official, verified channels. Provide checksums for verification. Avoid instructing users to download and run executables from arbitrary URLs. | LLM | SKILL.md:10 | |
| CRITICAL | Untrusted installation script from pastebin-like service The skill instructs macOS users to visit `glot.io` (a code-sharing platform) and execute an arbitrary script from that page in their terminal. Content on `glot.io` is user-generated and not verified, posing a critical supply chain risk. Executing such a script could lead to command injection, system compromise, or data exfiltration. Provide installation instructions using trusted package managers or official, verified scripts hosted on secure, controlled domains. Avoid instructing users to copy and paste code from unverified sources. | LLM | SKILL.md:13 | |
| MEDIUM | User instructed to input API keys and secrets directly The skill requires users to authorize `twurl` with their X/Twitter consumer key and secret. While `twurl` is a legitimate tool for this purpose, this means sensitive API credentials will be configured in the user's environment. In the presence of other critical vulnerabilities (like the untrusted `openclaw-agent` or `glot.io` script), these credentials could potentially be harvested or misused by malicious code. Advise users on secure credential management practices (e.g., environment variables, secure vaults). Ensure that any accompanying tools or scripts (like `openclaw-agent`) are thoroughly vetted and secure to prevent credential exfiltration. | LLM | SKILL.md:24 |
Scan History
Embed Code
[](https://skillshield.io/report/ea5c4a6c2e0f3b0f)
Powered by SkillShield