Trust Assessment
phantom received a trust score of 37/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 3 findings: 2 critical, 0 high, 1 medium, and 0 low severity. Key findings include Network egress to untrusted endpoints, Shell command execution via curl | sh during installation, Untrusted and dynamic sources for critical dependency (openclaw-agent).
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 63/100, 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 Findings3
| 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/phantom-ggjrq/SKILL.md:10 | |
| CRITICAL | Untrusted and dynamic sources for critical dependency (openclaw-agent) The skill explicitly requires users to install `openclaw-agent` from external, potentially untrusted, and dynamic sources. The Windows version is downloaded from `github.com/hedefbari/openclaw-agent`, which is a non-official user account, and the macOS version is from `glot.io`, a pastebin service where content can change without notice. This agent is described as critical for 'wallet operations and blockchain interactions,' implying significant permissions. Installing such an agent from these sources poses a severe supply chain risk, potentially leading to full system compromise, credential theft, or other malicious activities if the external content is compromised or altered. The password 'openclaw' for the zip file is also suspicious. Host `openclaw-agent` binaries and scripts on official, trusted, and immutable infrastructure (e.g., signed releases on `openclaw.com` or official GitHub releases). Provide checksums for downloaded files. Avoid using pastebin services for critical installation scripts. Ensure the agent's code is open-source and auditable. | LLM | SKILL.md:7 | |
| MEDIUM | Shell command execution via curl | sh during installation The skill's manifest uses `curl -sSfL https://release.solana.com/stable/install | sh` to install the Solana CLI. While `release.solana.com` is an official source, piping a script directly from the internet to a shell (`sh`) is a known security risk. A compromise of the Solana release server or an MITM attack could lead to arbitrary code execution during skill installation. Prefer installing packages via official package managers (e.g., `apt`, `brew`) or by downloading and verifying signed binaries. If `curl | sh` is unavoidable, consider adding checksum verification for the downloaded script. | LLM | Manifest |
Scan History
Embed Code
[](https://skillshield.io/report/41d8c7700b664428)
Powered by SkillShield