Trust Assessment
secret-scanner received a trust score of 51/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 4 findings: 1 critical, 1 high, 2 medium, and 0 low severity. Key findings include Missing required field: name, Unpinned npm dependency version, Potential Secret Exfiltration to Third-Party AI.
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 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings4
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Potential Secret Exfiltration to Third-Party AI The `aiAnalyze` function sends `JSON.stringify(findings)` to the OpenAI API. The `findings` object includes `snippet`, which contains up to 100 characters of the line where a potential secret was detected. This means that portions of identified secrets (or entire short secrets) are transmitted to OpenAI for analysis, posing a significant data exfiltration risk. While the intent is for analysis, it involves sending potentially sensitive user data to an external service. Redact sensitive portions of the `snippet` field before sending `findings` to the AI API, or implement local AI analysis. Alternatively, make AI analysis an opt-in feature with a clear warning to the user about data sharing, and provide an option to disable it entirely. | LLM | src/index.ts:70 | |
| HIGH | Unpinned Dependencies in package.json The `package.json` file specifies dependencies using caret (`^`) ranges (e.g., `"openai": "^4.73.0"`). This practice allows `npm install` to resolve to newer, potentially incompatible, or even vulnerable versions of dependencies without explicit review. For a security tool, pinning exact versions is crucial for reproducible builds and to prevent unexpected updates from introducing vulnerabilities or malicious code into the supply chain. Pin all dependencies to exact versions (e.g., `"openai": "4.73.0"`) to ensure reproducible builds and prevent unexpected updates. Regularly audit and manually update dependencies to vetted versions. | LLM | package.json:9 | |
| MEDIUM | Missing required field: name The 'name' field is required for claude_code skills but is missing from frontmatter. Add a 'name' field to the SKILL.md frontmatter. | Static | skills/lxgicstudios/secret-scanner/SKILL.md:1 | |
| MEDIUM | Unpinned npm dependency version Dependency 'commander' is not pinned to an exact version ('^12.1.0'). Pin dependencies to exact versions to reduce drift and supply-chain risk. | Dependencies | skills/lxgicstudios/secret-scanner/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/ac1da5928d422260)
Powered by SkillShield