Trust Assessment
silverback-defi received a trust score of 80/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Potential Command Injection in curl arguments, Unpinned npm dependency for MCP Server setup.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection in curl arguments The skill provides `curl` command examples where user-controlled input (e.g., `token`, `amount`, `walletAddress`, `message`, `strategy`, `pool`, `agentId`, `capability`) is embedded within JSON data passed via the `-d` flag. If the LLM constructs these `curl` commands by directly interpolating user input without proper shell escaping or JSON escaping, a malicious user could inject arbitrary shell commands. For instance, providing `{"token": "ETH"}' ; evil_command #"}` could break out of the JSON string and execute `evil_command`. The LLM must rigorously sanitize and escape all user-provided input before embedding it into JSON strings, and before embedding the JSON string into a shell command. Specifically, ensure that single quotes and other shell metacharacters are properly escaped or the JSON payload is passed via a file (e.g., `curl -d @payload.json`) to prevent shell injection. | LLM | SKILL.md:22 | |
| MEDIUM | Unpinned npm dependency for MCP Server setup The `SKILL.md` instructs users to install `silverback-x402-mcp` globally using `npm install -g silverback-x402-mcp`. This command does not specify a version, meaning it will always install the latest available version. This introduces a supply chain risk as a malicious update to the package or a breaking change in a future version could compromise the system or lead to unexpected behavior. Specify a fixed version for the `npm` package, e.g., `npm install -g silverback-x402-mcp@1.2.3`, or use a lock file mechanism if applicable, to ensure deterministic and secure dependency resolution. | LLM | SKILL.md:127 |
Scan History
Embed Code
[](https://skillshield.io/report/4ed9ec70132ff11a)
Powered by SkillShield