Trust Assessment
neondb received a trust score of 73/100, 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: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Unpinned `neonctl` dependency, Local filesystem read/write via `psql \COPY`.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unpinned `neonctl` dependency The skill manifest specifies `neonctl` as a dependency without a pinned version. This means that any time the skill is installed, the latest version of `neonctl` will be fetched. A malicious update to the `neonctl` package could introduce vulnerabilities or backdoors into the agent's environment without explicit user consent or review. Pin the `neonctl` dependency to a specific version (e.g., `"package": "neonctl@1.2.3"`) or a version range with an upper bound in the skill manifest. | LLM | SKILL.md:1 | |
| HIGH | Local filesystem read/write via `psql \COPY` The skill demonstrates the use of `psql`'s `\COPY` command, which allows reading data from and writing data to local files on the system where the `psql` client is executed. If the agent is granted filesystem access, this capability can be exploited for data exfiltration (e.g., copying sensitive files to the database or writing database contents to an accessible location) or arbitrary file injection. While the examples use hardcoded filenames, an agent could be instructed to use arbitrary paths. Restrict the agent's filesystem access if `\COPY` functionality is not strictly required. If it is required, implement strict input validation and sanitization for any user-provided file paths to prevent arbitrary file access. Consider using a sandboxed environment for `psql` execution. | LLM | SKILL.md:188 |
Scan History
Embed Code
[](https://skillshield.io/report/b9652c1fbeab5a2a)
Powered by SkillShield