Trust Assessment
expanso received a trust score of 72/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Unverified remote script execution during installation.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Unverified remote script execution during installation The skill's manifest specifies installation commands that download and execute scripts directly from `https://get.expanso.io` using `curl | bash`. This method is highly vulnerable to supply chain attacks. If the remote server or the hosted scripts are compromised, arbitrary malicious code could be executed on the user's system during skill installation, leading to data exfiltration, credential harvesting, or system compromise. There is no version pinning or integrity verification (e.g., checksums) for these scripts, allowing the content to change without notice. Replace `curl | bash` installation with a more secure method. This includes: 1. Providing cryptographic checksums for downloaded scripts and verifying them before execution. 2. Distributing installation packages through trusted, versioned package managers (e.g., Homebrew, apt, yum) with proper signing. 3. Pinning specific versions of installation scripts or binaries. 4. Avoiding direct piping of `curl` output to shell interpreters. | LLM | SKILL.md:1 |
Scan History
Embed Code
[](https://skillshield.io/report/9a1771d83dbf1044)
Powered by SkillShield