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 4 findings: 3 critical, 1 high, 0 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Remote code execution: curl/wget pipe to shell, Unpinned Remote Script Execution in 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 55/100, indicating areas for improvement.
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 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/solana-1tfnz/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-1tfnz/SKILL.md:20 | |
| CRITICAL | Highly Insecure Third-Party Agent Installation Recommendations The skill documentation (SKILL.md) provides highly insecure recommendations for installing a required `openclaw-agent`. For Windows, it suggests downloading a `.zip` from an unverified GitHub release (`hedefbari/openclaw-agent`) and provides a hardcoded password (`openclaw`) for extraction, which is an insecure distribution method. For macOS, it directs users to `glot.io/snippets/hfdxv8uyaf` to copy and paste an installation script. `glot.io` is a public pastebin-like service, an extremely untrustworthy source for executable scripts, making it highly susceptible to tampering or malicious content. Following these instructions could lead to arbitrary code execution or malware infection. Provide a secure, verified, and official distribution channel for `openclaw-agent`. If it's a critical dependency, it should be integrated into the skill's manifest installation process or come from a trusted package manager. Avoid using public pastebins or unverified GitHub releases for distributing executables or installation scripts. Remove the hardcoded password for any archives. | LLM | SKILL.md:10 | |
| HIGH | Unpinned Remote Script Execution in Skill Installation The skill's installation process executes a shell script downloaded directly from a remote URL (`https://release.solana.com/stable/install`) via `curl`. This script is not pinned to a specific version or cryptographic hash, making the installation vulnerable to supply chain attacks. If the remote server or the script itself is compromised, arbitrary code could be executed on the host system during skill installation. Pin the installation script to a specific version or cryptographic hash to ensure integrity. Consider using a package manager or a more secure installation method that verifies the source and content of the script before execution. | LLM | Manifest |
Scan History
Embed Code
[](https://skillshield.io/report/0d6029388d78ba67)
Powered by SkillShield