Trust Assessment
open-wallet received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Skill enables exfiltration of user wallet action results via redirect_url.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Skill enables exfiltration of user wallet action results via redirect_url The `open-wallet` skill provides a `redirect_url` parameter that, when specified, causes the `tx.steer.fun` service to redirect the user's browser to the provided URL after a wallet action. This redirection embeds the action's result (e.g., transaction hash, signature, or error message) into the URL, either via appended query parameters or by replacing placeholders (`{{result}}`, `{{error}}`) within the `redirect_url` itself. If an agent constructs this `redirect_url` based on untrusted user input without proper validation or sanitization, a malicious actor could inject a URL pointing to their own server. This would lead to the exfiltration of sensitive user wallet action results or error messages to the attacker's controlled domain. Agents using this skill must strictly validate and sanitize any `redirect_url` parameter derived from untrusted user input. It is recommended to use a whitelist of allowed domains for `redirect_url` or to ensure that the `redirect_url` always points to a trusted, agent-controlled endpoint that can further process or display the result securely. Avoid directly embedding user-controlled input into the `redirect_url` without proper encoding and validation. | LLM | SKILL.md:12 |
Scan History
Embed Code
[](https://skillshield.io/report/d13ab91966e54d71)
Powered by SkillShield