Trust Assessment
sql-writer received a trust score of 67/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 2 findings: 1 critical, 0 high, 1 medium, and 0 low severity. Key findings include Unpinned external dependency and arbitrary code execution via `npx`, External transmission of potentially sensitive data.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 63/100, 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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Unpinned external dependency and arbitrary code execution via `npx` The skill documentation recommends using `npx ai-sql` which executes an external package from the npm registry without specifying a version. This creates a critical supply chain risk, as a malicious update to the `ai-sql` package could lead to arbitrary code execution on the host system. Furthermore, if the host LLM or a user executes these commands, it directly runs untrusted code, posing a command injection threat. Implement strict sandboxing for any execution of `npx` or similar package manager commands. Always specify a pinned version for `npx` commands (e.g., `npx ai-sql@1.2.3`) to mitigate supply chain risks. Validate and sanitize all inputs passed to external tools. Advise users to audit the `ai-sql` package before execution. | LLM | SKILL.md:10 | |
| MEDIUM | External transmission of potentially sensitive data The `ai-sql` tool, as described in the skill, sends natural language queries and optional database schema information to an external AI model for processing. If sensitive data (e.g., PII in queries, detailed schema of confidential databases) is provided as input, it will be transmitted to a third-party service, which could pose privacy and data security risks depending on the service's policies and security posture. Advise users to avoid passing sensitive or confidential information to the `ai-sql` tool, especially when providing schema context. Recommend reviewing the privacy policy and security practices of the underlying AI service used by `ai-sql`. | LLM | SKILL.md:59 |
Scan History
Embed Code
[](https://skillshield.io/report/25be164cfa2fa94f)
Powered by SkillShield