Trust Assessment
celo-rpc received a trust score of 86/100, 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, 0 medium, and 1 low severity. Key findings include Potential Command Injection via unsanitized shell commands, Unpinned dependency in installation instructions.
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 14, 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 via unsanitized shell commands The skill provides `bash` code examples using `cast` and `curl` that incorporate parameters such as addresses, RPC URLs, and transaction hashes. If the AI agent constructs and executes these shell commands by directly interpolating user-provided input without proper sanitization or escaping, a malicious user could inject arbitrary shell commands. For instance, a crafted address or RPC URL could contain shell metacharacters, leading to unauthorized command execution on the host system. Implement robust input validation and sanitization for all user-provided parameters before constructing and executing shell commands. Use libraries or functions that properly escape shell metacharacters. Alternatively, avoid direct shell execution for user-controlled inputs and use dedicated libraries (e.g., `viem` in TypeScript) for interacting with RPC endpoints, which handle parameter serialization more safely. | LLM | SKILL.md:100 | |
| LOW | Unpinned dependency in installation instructions The `npm install viem` command does not specify a version, which can lead to non-deterministic builds and potential compatibility issues or unexpected behavior if a new major version introduces breaking changes or vulnerabilities. While `viem` is a reputable library, pinning dependencies is a best practice for supply chain security. Specify a precise version or a version range for dependencies, e.g., `npm install viem@^X.Y.Z` or `npm install viem@X.Y.Z`. | LLM | SKILL.md:71 |
Scan History
Embed Code
[](https://skillshield.io/report/e9770dfde69fd438)
Powered by SkillShield