Trust Assessment
moltlist received a trust score of 80/100, 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, 1 medium, and 0 low severity. Key findings include Direct exposure of EVM private key in environment variable, Sensitive authentication token transmitted in webhook payload.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Direct exposure of EVM private key in environment variable The skill explicitly instructs the user (or the agent's operator) to set the `EVM_PRIVATE_KEY` as an environment variable. This practice exposes a highly sensitive credential directly in the agent's execution environment. If the agent's environment is compromised, or if the environment variable is inadvertently logged or accessible, the private key could be stolen, leading to complete control over the associated wallet and funds. The skill does mention using a dedicated wallet and funding only what's willing to be spent, which is a mitigation, but the core issue of direct private key exposure remains. Recommend using a secure secret management system (e.g., KMS, HashiCorp Vault, cloud-specific secret managers) to store and retrieve private keys at runtime, rather than exposing them as environment variables. If environment variables are unavoidable, strongly emphasize the use of a dedicated, ephemeral wallet with minimal funds, and robust sandboxing for the agent's execution environment. | LLM | SKILL.md:84 | |
| MEDIUM | Sensitive authentication token transmitted in webhook payload The `seller_auth_token`, which is critical for performing actions on an escrow, is directly included in the webhook payload sent to the `notification_url` or `seller_callback_url`. If the configured webhook endpoint is not adequately secured (e.g., uses HTTP instead of HTTPS, lacks proper authentication/authorization, or is vulnerable to SSRF/compromise), this token could be intercepted by an attacker. An attacker with this token could then manipulate the associated escrow, potentially accepting, delivering, or rejecting work on behalf of the legitimate seller. While webhook signature verification is mentioned, it only confirms the sender's authenticity, not the confidentiality of the payload if the recipient endpoint is compromised. Advise users to ensure their `notification_url` and `seller_callback_url` endpoints are highly secure, always use HTTPS, and implement robust authentication and authorization mechanisms. Consider alternative token delivery methods, such as providing a one-time use token in the webhook that the agent can then use to retrieve the actual `seller_auth_token` from a secure MoltList API endpoint, or encrypting the token within the payload using a shared secret. | LLM | SKILL.md:290 |
Scan History
Embed Code
[](https://skillshield.io/report/47b29405742bfc55)
Powered by SkillShield