Trust Assessment
Neon Automation 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 Skill exposes database connection URIs containing credentials, Skill allows creation of new API keys.
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 20, 2026 (commit 27904475). 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 | Skill exposes database connection URIs containing credentials The `NEON_GET_PROJECT_CONNECTION_URI` tool returns a full Postgres connection string, which explicitly includes sensitive credentials. Although the skill documentation warns users to treat it as a secret, a compromised or misconfigured LLM agent could log, display, or otherwise expose these credentials, leading to unauthorized database access. This constitutes a data exfiltration risk if the LLM's output is not properly secured. Implement strict output filtering and redaction policies for LLM responses when this tool is invoked. Ensure the LLM environment prevents logging of sensitive outputs. Consider if the full URI needs to be returned to the LLM, or if a tokenized/redacted version could suffice for certain operations, with the full URI only accessible in a secure, ephemeral context. | LLM | SKILL.md:70 | |
| HIGH | Skill allows creation of new API keys The `NEON_CREATE_API_KEY_FOR_ORGANIZATION` tool grants the ability to generate new API keys for an organization. This is a highly privileged operation. If an LLM agent is compromised or manipulated, it could be used to create new, unauthorized API keys, leading to persistent access for an attacker, bypassing existing security controls or user revocation. This represents an excessive permission for an automated agent without strong human-in-the-loop approval for such critical actions. Implement strict access controls and human-in-the-loop approval for the `NEON_CREATE_API_KEY_FOR_ORGANIZATION` tool. Limit its availability to only highly trusted and audited contexts. Consider if this functionality is truly necessary for an automated skill or if it should be restricted to direct human interaction. | LLM | SKILL.md:118 |
Scan History
Embed Code
[](https://skillshield.io/report/39ed96bd8671e5c2)
Powered by SkillShield