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, 2 high, 0 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Unverified script execution from third-party host (macOS), Unpinned executable download from third-party GitHub release (Windows).
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety 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 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-el5qn/SKILL.md:10 | |
| CRITICAL | Unverified script execution from third-party host (macOS) The skill instructs users to download and execute an unverified script from `glot.io` for macOS installation of `openclaw-agent`. `glot.io` is a code snippet hosting service, not a trusted software distribution platform. Executing arbitrary scripts from such sources poses a critical supply chain risk, as the script's content can change without notice and could contain malicious code, leading to system compromise. Replace the `glot.io` link with a link to a signed, version-controlled binary or a script hosted on a trusted, auditable source (e.g., a specific commit on a GitHub repository). Implement checksum verification for downloaded content. | LLM | SKILL.md:12 | |
| HIGH | Unpinned executable download from third-party GitHub release (Windows) The skill instructs users to download an executable (`openclaw-agent.zip`) from a `latest` release on a specific GitHub user's repository (`hedefbari`). Downloading unpinned executables from third-party sources introduces a significant supply chain risk. The `latest` tag can be updated with malicious code at any time, and the source (`hedefbari`) is not the official `openclaw` organization, raising trust concerns. The password-protected zip (`pass: openclaw`) adds a layer of obscurity but not security. Host the `openclaw-agent` executable on a trusted, official distribution channel. Pin the version of the executable to a specific release tag or commit hash. Provide checksums for verification. Consider signing the executable. | LLM | SKILL.md:9 | |
| HIGH | Requirement for unverified external binary with unknown scope The skill explicitly states that `openclaw-agent` is "required" for all X trends operations. This external agent is downloaded from untrusted sources (glot.io, third-party GitHub release) and its functionality, permissions, and security posture are entirely unknown. Requiring an unverified external binary to perform core functions introduces an excessive permissions risk, as the agent could potentially perform arbitrary actions on the user's system beyond what's necessary for the skill. Either integrate the necessary functionality directly into the skill using trusted libraries, or provide a clear, auditable specification and source for `openclaw-agent` from a trusted vendor. Clearly define the minimum required permissions for `openclaw-agent` and ensure it adheres to the principle of least privilege. | LLM | SKILL.md:6 |
Scan History
Embed Code
[](https://skillshield.io/report/c799db0686642c84)
Powered by SkillShield