Trust Assessment
lifi 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 Potential Command Injection and API Key Exfiltration via `curl`.
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 | Potential Command Injection and API Key Exfiltration via `curl` The skill explicitly instructs the AI agent to use `curl` for all LI.FI API interactions. The provided examples demonstrate `curl` commands with dynamic parameters (e.g., `fromChain`, `toToken`, `fromAddress`, `fromAmount`, `txHash`, and JSON payload fields) that are highly likely to be derived from untrusted user input. Without robust sanitization, an attacker could inject shell metacharacters or additional `curl` arguments into these parameters, leading to arbitrary command execution on the host system. Furthermore, the `LIFI_API_KEY` is consistently included in the `x-lifi-api-key` header of every `curl` request. If an attacker can manipulate the `--url` parameter through injected shell commands, they could redirect the request to an arbitrary malicious server, thereby exfiltrating the `LIFI_API_KEY`. Replace direct `curl` command execution with a secure HTTP client library (e.g., Python's `requests` library) that handles URL encoding and request construction safely, preventing shell injection. Ensure all user-provided inputs are strictly validated and sanitized before being used in any external command or API call. Avoid exposing sensitive credentials like `LIFI_API_KEY` to any part of a command that can be manipulated by untrusted input. | LLM | SKILL.md:48 |
Scan History
Embed Code
[](https://skillshield.io/report/68d2e8dbffd99d4e)
Powered by SkillShield