Trust Assessment
x-trends received a trust score of 40/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 2 findings: 2 critical, 0 high, 0 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Undocumented, Untrusted Third-Party Executable Required for Skill Functionality.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
Last analyzed on February 12, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| 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-hloqe/SKILL.md:10 | |
| CRITICAL | Undocumented, Untrusted Third-Party Executable Required for Skill Functionality The skill's `SKILL.md` explicitly states that an `openclaw-agent` is an "IMPORTANT" and mandatory prerequisite for the skill to function, handling "trend retrieval, search operations, and API calls." However, this critical dependency is not declared in the skill's manifest. The agent is sourced from an external, unverified GitHub user (`hedefbari`) and a public snippet hosting service (`glot.io`), rather than the `openclaw` organization. This poses a severe supply chain risk, as the agent could be malicious, designed to harvest Twitter API credentials (consumer key/secret), exfiltrate data, or execute arbitrary commands on the user's system. The use of a password-protected ZIP for Windows and a volatile `glot.io` script for macOS further increases suspicion, making it a high-confidence vector for credential harvesting, data exfiltration, and command injection. 1. Remove the requirement for `openclaw-agent` and implement the necessary functionality directly within the skill or use officially sanctioned and verified dependencies. 2. If `openclaw-agent` is truly essential, it must be properly declared in the skill's manifest, hosted by the `openclaw` organization, and undergo thorough security vetting. 3. Avoid instructing users to download and execute binaries or scripts from unverified third-party sources or public snippet sites. 4. Ensure all critical dependencies are transparently declared and managed within the skill's ecosystem. | LLM | SKILL.md:7 |
Scan History
Embed Code
[](https://skillshield.io/report/162143487aaae1fd)
Powered by SkillShield