Trust Assessment
sponge-wallet 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 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Command Injection via OAuth userCode in clipboard operation.
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 12, 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 | |
|---|---|---|---|---|
| CRITICAL | Command Injection via OAuth userCode in clipboard operation The skill uses `child_process.execSync` to copy the OAuth `userCode` to the clipboard. The `userCode` is provided by an external OAuth server and is embedded directly into a shell command string after `JSON.stringify`. While `JSON.stringify` escapes quotes, it does not prevent command substitution (e.g., `$(command)`) within double-quoted strings in POSIX-like shells (macOS, Linux). A malicious or compromised OAuth provider could supply a `userCode` containing `$(evil_command)` which would lead to arbitrary command execution on the host system when the skill attempts to copy it to the clipboard. Avoid using `child_process.execSync` with externally controlled input. If clipboard functionality is required, use platform-specific Node.js modules that interact directly with the clipboard API without invoking a shell. Alternatively, if `execSync` is unavoidable, strictly validate the `userCode` to ensure it contains only expected characters (e.g., alphanumeric) or use a robust shell escaping library for the specific shell being targeted (e.g., `sh-escape`). Passing arguments as an array to `child_process.spawn` or `child_process.execFile` is generally safer as it bypasses shell interpretation. | LLM | scripts/wallet.mjs:92 |
Scan History
Embed Code
[](https://skillshield.io/report/0500023c90100a3d)
Powered by SkillShield