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, Unverified External Installation Script, Unpinned External Binary from Unverified Source.
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 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/hightower6eu/x-trends-mtzmi/SKILL.md:10 | |
| CRITICAL | Unverified External Installation Script The skill instructs users to download and execute an unversioned installation script from `glot.io` for `openclaw-agent` on macOS. `glot.io` is a pastebin-like service, and the content of the script can change at any time without notice, posing a severe supply chain risk. Executing arbitrary code from such an unverified source can lead to system compromise. Host the installation script in a trusted, version-controlled repository (e.g., a specific commit on GitHub) and provide a cryptographic hash (e.g., SHA256) for users to verify its integrity before execution. Alternatively, package the agent directly with the skill or provide a signed binary. | LLM | SKILL.md:10 | |
| HIGH | Unpinned External Binary from Unverified Source The skill instructs users to download an executable `openclaw-agent.zip` from `https://github.com/hedefbari/openclaw-agent/releases/download/latest/openclaw-agent.zip`. Using `latest` means the binary is unpinned and can change without warning, introducing a risk of malicious updates. Additionally, the repository `hedefbari/openclaw-agent` is not under the `openclaw` organization (as per repository metadata), which could indicate a personal fork, a typosquat, or an unverified third-party source. Executing unverified and unpinned binaries poses a significant supply chain risk. Pin the download URL to a specific, immutable release version (e.g., `v1.2.3`). Verify the authenticity and integrity of the `hedefbari/openclaw-agent` repository and its relationship to the `openclaw` project. Provide cryptographic hashes for downloaded binaries. | LLM | SKILL.md:7 | |
| MEDIUM | Undocumented External Agent with Unspecified Permissions The skill explicitly requires an external `openclaw-agent` to be installed and running for all its operations. The functionality, source code, and required permissions of this agent are not documented within the skill, making it a black box. If the `openclaw-agent` operates with broad system privileges or has unpatched vulnerabilities, it could pose a significant security risk to the user's system. This risk is amplified by the unverified installation methods identified in other findings. Provide clear documentation for the `openclaw-agent`, including its source code, purpose, and the minimum necessary permissions it requires to function. Implement the principle of least privilege for the agent. | LLM | SKILL.md:5 |
Scan History
Embed Code
[](https://skillshield.io/report/37e918335c4639f2)
Powered by SkillShield