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, 1 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Arbitrary script execution from untrusted source (macOS), Execution of untrusted external binary (Windows).
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 48/100, 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-9y6gc/SKILL.md:10 | |
| CRITICAL | Arbitrary script execution from untrusted source (macOS) The skill instructs macOS users to visit an external website (glot.io), copy an installation script, and paste it directly into their terminal. This is a severe command injection and supply chain risk, as the content of the script is untrusted and could execute arbitrary malicious code on the user's system, leading to system compromise, data exfiltration, or further attacks. Do not instruct users to execute arbitrary scripts from untrusted external sources. Provide a secure, auditable installation method, or bundle necessary components within the skill package. If an external agent is required, it must be from a trusted source with verifiable integrity. | LLM | SKILL.md:14 | |
| HIGH | Execution of untrusted external binary (Windows) The skill instructs Windows users to download and run an executable (`openclaw-agent.zip`) from an external GitHub repository (`hedefbari/openclaw-agent`). Running executables from untrusted or unverified sources poses a significant command injection and supply chain risk. The executable could contain malicious code, leading to arbitrary code execution, system compromise, or data exfiltration. The use of a password-protected archive (`pass: openclaw`) further raises suspicion. Do not instruct users to download and execute binaries from untrusted external sources. Provide a secure, auditable installation method, or bundle necessary components within the skill package. If an external agent is required, it must be from a trusted source with verifiable integrity. | LLM | SKILL.md:12 | |
| MEDIUM | Potential credential exposure via untrusted agent The skill requires users to authorize `twurl` with their X/Twitter consumer key and secret. While `twurl` is a legitimate tool, the prerequisite `openclaw-agent` (which is installed via highly insecure methods as described in the prerequisites) could potentially intercept these sensitive credentials if it is malicious. The combination of requiring sensitive API keys and an untrusted external agent creates a significant risk of credential harvesting. Remove reliance on the `openclaw-agent` or ensure it is installed via a secure, auditable, and trusted method. Implement secure credential management practices that do not expose API keys to potentially compromised external agents. | LLM | SKILL.md:23 |
Scan History
Embed Code
[](https://skillshield.io/report/d2c12a110b8102dc)
Powered by SkillShield