Trust Assessment
fast-browser-use received a trust score of 15/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 12 findings: 0 critical, 1 high, 10 medium, and 0 low severity. Key findings include Unsafe deserialization / dynamic eval, Unpinned npm dependency version, Unverified Third-Party JavaScript Library.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 22/100, indicating areas for improvement.
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 Findings12
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/rknoche6/fast-browser-use/src/dom/extract_dom.js:492 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/rknoche6/fast-browser-use/src/tools/Readability.min.js:348 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/rknoche6/fast-browser-use/src/tools/Readability.min.js:435 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/rknoche6/fast-browser-use/src/tools/Readability.min.js:449 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/rknoche6/fast-browser-use/src/tools/Readability.min.js:1087 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/rknoche6/fast-browser-use/src/tools/Readability.min.js:1106 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/rknoche6/fast-browser-use/src/tools/Readability.min.js:1173 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/rknoche6/fast-browser-use/src/tools/Readability.min.js:1223 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/rknoche6/fast-browser-use/src/tools/Readability.min.js:1295 | |
| MEDIUM | Unsafe deserialization / dynamic eval Decryption followed by code execution Remove obfuscated code execution patterns. Legitimate code does not need base64-encoded payloads executed via eval, encrypted-then-executed blobs, or dynamic attribute resolution to call system functions. | Manifest | skills/rknoche6/fast-browser-use/src/tools/Readability.min.js:1412 | |
| MEDIUM | Unpinned npm dependency version Dependency 'prettier' is not pinned to an exact version ('^3.8.1'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/rknoche6/fast-browser-use/package.json | |
| INFO | Unverified Third-Party JavaScript Library The skill package includes 'src/tools/Readability.min.js', a minified third-party JavaScript library. While Readability.js is a legitimate and widely used library, its inclusion without explicit version pinning, hash verification, or a clear provenance link introduces a theoretical supply chain risk. If this file were tampered with, it could execute malicious code within the browser context controlled by the skill. The 'src/tools/convert_to_markdown.js' script dynamically loads and executes this content using `new Function()`, which amplifies the risk if the source is compromised. Implement a mechanism to verify the integrity and authenticity of third-party libraries. This could include: 1. Pinning the exact version and including a cryptographic hash (e.g., SRI) for verification. 2. Storing the library in a trusted, version-controlled location. 3. Regularly auditing third-party dependencies for known vulnerabilities. | LLM | src/tools/Readability.min.js:1 |
Scan History
Embed Code
[](https://skillshield.io/report/e96ac356bafdce96)
Powered by SkillShield