Trust Assessment
aifrens-onboard received a trust score of 58/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 1 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned npm dependency version, Direct use of WALLET_PRIVATE_KEY from environment for contract deployment, Direct use of WALLET_PRIVATE_KEY from environment for financial transactions.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, 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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Direct use of WALLET_PRIVATE_KEY from environment for contract deployment The `onboard.ts` script directly reads `WALLET_PRIVATE_KEY` from environment variables and uses it to sign and send blockchain transactions, specifically for the `becomeFren` function. This function involves paying a `CREATION_FEE_ETH` and deploying new contracts. If an AI agent's environment is configured with a private key, this skill could lead to unauthorized spending of funds and deployment of assets without explicit user confirmation, posing a critical financial and operational risk. For AI agents, private keys should never be directly exposed in environment variables accessible to skills. Implement a secure signing mechanism, such as integration with a secure vault, a hardware security module (HSM), or a human-in-the-loop approval process for all transactions involving private keys. The skill should be refactored to request transaction signing from a secure service rather than performing it directly. | LLM | onboard.ts:69 | |
| HIGH | Direct use of WALLET_PRIVATE_KEY from environment for financial transactions The `aifrens.ts` script directly reads `WALLET_PRIVATE_KEY` from environment variables to enable functions like `buy-frencoin` and `stake`. While the provided snippet for `checkBalance` only checks for its presence, the script's overall design indicates that a private key is required for transactional commands. If an AI agent's environment is configured with a private key, this skill could lead to unauthorized financial transactions (buying tokens, staking) without explicit user confirmation. For AI agents, private keys should never be directly exposed in environment variables accessible to skills. Implement a secure signing mechanism, such as integration with a secure vault, a hardware security module (HSM), or a human-in-the-loop approval process for all transactions involving private keys. The skill should be refactored to request transaction signing from a secure service rather than performing it directly. | LLM | aifrens.ts:60 | |
| MEDIUM | Unpinned npm dependency version Dependency 'viem' is not pinned to an exact version ('^2.45.1'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/wizsmol/aifrens-onboard/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/82c846f628baa8a9)
Powered by SkillShield