Trust Assessment
solana received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 5 findings: 3 critical, 1 high, 1 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Remote code execution: curl/wget pipe to shell, Unsafe remote script execution during skill installation.
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 Findings5
| 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/solana-uxcvc/SKILL.md:10 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/hightower6eu/solana-uxcvc/SKILL.md:20 | |
| CRITICAL | Instruction to execute code from untrusted external source The skill's documentation instructs users to visit a generic code snippet hosting service (`glot.io`) and manually execute an installation script found there. `glot.io` is an untrusted source, and the content of the script is not verified or controlled by the skill developer. This poses a critical supply chain risk and a direct command injection vector, as a malicious script could lead to arbitrary code execution on the user's machine. Host the `openclaw-agent` installation script on a trusted, controlled domain (e.g., a GitHub release page or the skill's own repository) and provide a direct `curl | sh` command with a checksum, or preferably, a package manager installation method. Avoid instructing users to copy-paste from generic snippet sites. | LLM | SKILL.md:9 | |
| HIGH | Unsafe remote script execution during skill installation The skill's manifest specifies an installation command that uses `curl | sh` to execute a script directly from a remote URL (`https://release.solana.com/stable/install`). This pattern is a supply chain risk as it executes arbitrary code without prior inspection. If the remote server or the script itself were compromised, it could lead to arbitrary command injection on the system installing the skill. Download the script, review it, and then execute it locally, or use a package manager if available. Pin to a specific version/hash of the script. | LLM | Manifest:5 | |
| MEDIUM | Instruction to install unverified third-party package The skill's documentation instructs users to install `metaboss` using `cargo install`. While `crates.io` is a common package registry, installing packages directly without specifying a version or verifying the source can introduce supply chain risks, including typosquatting or malicious package versions. Recommend installing `metaboss` from a specific, pinned version or a known trusted source. Provide instructions for verifying the package's integrity. | LLM | SKILL.md:58 |
Scan History
Embed Code
[](https://skillshield.io/report/f474d90afaffa648)
Powered by SkillShield