Trust Assessment
wallet-tracker received a trust score of 65/100, 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, 0 medium, and 0 low severity. Key findings include Instruction to execute arbitrary script from untrusted pastebin, Instruction to download and run executable from unverified source with suspicious password, Unpinned dependency in manifest.
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 12, 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 | Instruction to execute arbitrary script from untrusted pastebin The skill instructs users to copy and paste an installation script from `glot.io`, a public code pastebin service. Running scripts from such sources is highly dangerous as the content can be arbitrary, malicious, and change without notice, leading to potential system compromise. This is a direct instruction to execute untrusted code from an untrusted source. Remove the instruction to download/execute scripts from `glot.io`. Provide a trusted, version-controlled installation method (e.g., official package manager, signed binaries, or a well-maintained GitHub repository with clear installation instructions and checksums). | LLM | SKILL.md:9 | |
| HIGH | Instruction to download and run executable from unverified source with suspicious password The skill instructs users to download an executable (`openclaw-agent.zip`) from a specific GitHub user's repository (`hedefbari`) and provides a password (`openclaw`) to extract it. While GitHub releases are common, downloading and running executables from individual user accounts without further verification (e.g., official organization, signed binaries, checksums) carries inherent supply chain risks. The requirement for a password to extract a public utility is highly unusual and suspicious, potentially indicating an attempt to bypass security scans or obscure content. Provide a more trusted and verifiable source for `openclaw-agent`, such as an official project page, a well-known package manager, or signed binaries with checksums. Remove the unusual password requirement for extraction. | LLM | SKILL.md:7 | |
| INFO | Unpinned dependency in manifest The `requests` package is specified without a version constraint in the manifest. This can lead to non-deterministic builds and potential compatibility issues or security vulnerabilities if a new, incompatible, or compromised version is released. Pin the `requests` dependency to a specific version (e.g., `"requests==2.28.1"`) or a version range (e.g., `"requests>=2.28.1,<3.0.0"`) to ensure consistent and secure installations. | LLM | SKILL.md |
Scan History
Embed Code
[](https://skillshield.io/report/097bfc72a7f49d5b)
Powered by SkillShield