Trust Assessment
usd1-wlf-transfer received a trust score of 51/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 5 findings: 1 critical, 1 high, 3 medium, and 0 low severity. Key findings include Missing required field: name, Unpinned npm dependency version, Direct Private Key Input.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 48/100, 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 Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Direct Private Key Input The skill requires a 'privateKey' as a direct input parameter. Providing cryptographic private keys to an LLM-orchestrated skill is an extreme security risk, as it exposes the key to the LLM's context and potential logging, making it vulnerable to exfiltration or misuse. LLMs should never directly handle or be given private keys. Redesign the skill to avoid direct input of private keys. Instead, use secure key management systems (e.g., hardware wallets, KMS, or secure enclaves) where the private key never leaves the secure environment. The skill should interact with an abstraction layer that signs transactions without ever seeing the private key itself. | LLM | index.js:4 | |
| HIGH | Unpinned Dependencies in package.json The package.json file uses unpinned dependencies ('*') for critical libraries like '@wormhole-foundation/sdk' and '@wormhole-foundation/sdk-base'. This allows for arbitrary version updates, which can introduce breaking changes, vulnerabilities, or even malicious code without explicit review, posing a significant supply chain risk. Pin all dependencies to specific versions (e.g., '1.2.3') or use caret ( '^1.2.3') or tilde ('~1.2.3') ranges to ensure predictable and secure dependency resolution. Regularly audit and update dependencies. | LLM | package.json:6 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/asgherali/usd1-wlf-transfer/SKILL.md:1 | |
| MEDIUM | Unpinned npm dependency version Dependency '@wormhole-foundation/sdk' is not pinned to an exact version ('*'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/asgherali/usd1-wlf-transfer/package.json | |
| MEDIUM | Direct Error Message Exposure The skill directly returns 'error.message' from a catch block. If the underlying Wormhole SDK or other dependencies produce error messages that contain sensitive information (e.g., parts of the private key, transaction details, or internal system paths), this could lead to data exfiltration. Sanitize or generalize error messages before returning them to the user. Avoid exposing raw error messages from internal libraries. Log detailed errors internally for debugging but provide generic, user-friendly messages externally. | LLM | index.js:28 |
Scan History
Embed Code
[](https://skillshield.io/report/4980a7066653a929)
Powered by SkillShield