Trust Assessment
clawdwallet received a trust score of 77/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 3 findings: 0 critical, 1 high, 2 medium, and 0 low severity. Key findings include Unpinned dependencies and direct git clone from untrusted source, High-privilege Chrome extension in Developer Mode, Handling of sensitive mnemonics and unauthenticated WebSocket communication.
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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned dependencies and direct git clone from untrusted source The skill instructs the agent developer to clone a repository directly from GitHub (`https://github.com/NeOMakinG/clawdwallet.git`) and then run `npm install`. This introduces significant supply chain risks. If the GitHub repository is compromised, or if any of its `npm` dependencies are malicious (e.g., typosquats, compromised packages), the installed wallet extension will be compromised. The `npm install` command does not specify pinned versions, increasing the risk of pulling in vulnerable or malicious packages. Recommend using a trusted, audited source for the wallet extension. If building from source, pin all dependencies to specific, known-good versions (e.g., via `package-lock.json` or explicit version numbers) and include integrity checks. Consider using a pre-built, signed binary from a trusted source instead of building from untrusted source code. | LLM | SKILL.md:9 | |
| MEDIUM | High-privilege Chrome extension in Developer Mode The skill requires loading a Chrome extension in 'Developer mode' by selecting the `dist/` folder. This grants the extension extensive permissions within the browser environment, including access to all web pages, local storage, and potentially other browser data. While necessary for a wallet extension's functionality, this broad scope means that if the extension itself is compromised (e.g., via a supply chain attack), it could lead to significant data exfiltration, credential harvesting, or unauthorized actions within the user's browser. Users should be extremely cautious when installing extensions in developer mode, especially from untrusted sources. Ensure the extension's code has been thoroughly audited. Consider running such an agent/extension in an isolated environment (e.g., a dedicated virtual machine or browser profile) to limit potential damage. | LLM | SKILL.md:17 | |
| MEDIUM | Handling of sensitive mnemonics and unauthenticated WebSocket communication The skill allows initializing a wallet with a mnemonic phrase (`"mnemonic": "your twenty four words..."`). This is a highly sensitive credential. The skill also communicates via a WebSocket (`ws://localhost:3033/clawdwallet`). If the WebSocket connection is not properly secured (e.g., lacks authentication, encryption, or origin validation), an attacker could potentially intercept mnemonics, transaction details, or gain unauthorized control over the wallet. While the skill warns against exposing mnemonics, the mechanism for handling them and the WebSocket's security are not detailed, leaving a potential vulnerability for credential harvesting or data exfiltration if the agent or environment is compromised. Implement robust authentication and encryption for the WebSocket connection. Ensure strict input validation and sanitization for all commands, especially those involving sensitive data like mnemonics. Agents should be designed to never expose mnemonics directly in logs or to untrusted outputs. Consider using hardware security modules or secure enclaves for mnemonic storage and transaction signing. | LLM | SKILL.md:22 |
Scan History
Embed Code
[](https://skillshield.io/report/f9e0ad4601da19b6)
Powered by SkillShield