Trust Assessment
1ly-payments 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 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Direct exposure of cryptographic wallet keys to external process, Unpinned dependencies 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 | Direct exposure of cryptographic wallet keys to external process The skill requires the user to configure environment variables `ONELY_WALLET_SOLANA_KEY` and `ONELY_WALLET_EVM_KEY` with direct access to cryptographic wallet keys, either inline or via file paths. These keys are then accessible to the `mcporter` process, which runs the `@1ly/mcp-server`. This grants the external MCP server direct access to highly sensitive financial credentials, posing a significant risk if the server or its dependencies are compromised. While necessary for the skill's functionality, this method of key handling increases the attack surface. Implement a more secure method for handling cryptographic keys, such as using hardware security modules (HSMs), secure enclaves, or a dedicated wallet service that does not expose raw private keys to the agent's execution environment. If direct key access is unavoidable, ensure the `mcporter` and `@1ly/mcp-server` packages are thoroughly audited and run in a highly isolated environment with minimal permissions. | LLM | SKILL.md:28 | |
| HIGH | Unpinned dependencies in installation instructions The skill's setup instructions `npm install -g mcporter` and `mcporter config add 1ly --command "npx @1ly/mcp-server"` do not specify exact versions for the `mcporter` or `@1ly/mcp-server` packages. This means the latest available versions will be installed and executed, which introduces a supply chain risk. A malicious update or a breaking change in a future version of these packages could lead to security vulnerabilities, unexpected behavior, or compromise of the agent's environment without explicit user action. Pin all dependencies to specific, known-good versions (e.g., `npm install -g mcporter@1.2.3` and `npx @1ly/mcp-server@4.5.6`). Regularly review and update these pinned versions after security audits and compatibility checks to mitigate risks from new vulnerabilities while maintaining control over the installed software. | LLM | SKILL.md:23 |
Scan History
Embed Code
[](https://skillshield.io/report/c6693ace6206b50f)
Powered by SkillShield