Security Audit
nextdns-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
nextdns-automation received a trust score of 93/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 1 medium, and 1 low severity. Key findings include Potential Prompt Injection via RUBE_SEARCH_TOOLS natural language parameters, Broad access to Nextdns operations via Rube MCP tools.
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 17, 2026 (commit 99e2a295). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Potential Prompt Injection via RUBE_SEARCH_TOOLS natural language parameters The skill instructs the LLM to use `RUBE_SEARCH_TOOLS` with `use_case` and `known_fields` parameters. These parameters are designed for natural language input (e.g., `use_case: "your specific Nextdns task"`). If the Rube MCP (which processes these calls) internally uses an LLM to interpret these natural language queries, a malicious user could craft these inputs to perform prompt injection against the Rube MCP's LLM, potentially manipulating its behavior, tool selection, or information retrieval process. The Rube MCP should implement robust input sanitization, guardrails, and strict parsing for `use_case` and `known_fields` parameters to prevent prompt injection against its internal LLM. The skill developer should also be cautious when passing unsanitized user input directly into these fields. | LLM | SKILL.md:35 | |
| LOW | Broad access to Nextdns operations via Rube MCP tools The skill leverages the Rube MCP, which provides tools like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. These tools, in conjunction with `RUBE_SEARCH_TOOLS`, allow the LLM to discover and execute a wide range of Nextdns operations. While this is the intended functionality of the Rube MCP, it means that if the LLM is compromised or given a malicious prompt, it could perform extensive and potentially destructive actions on the user's Nextdns configuration due to the broad scope of available operations. The skill itself does not define granular permissions, but rather exposes the full capabilities of the connected Nextdns toolkit through Rube MCP. Implement granular access controls within the Rube MCP for specific Nextdns operations, allowing users to scope the permissions granted to the LLM. The LLM should also be instructed to confirm sensitive or broad-impact operations with the user before execution. | LLM | SKILL.md:57 |
Scan History
Embed Code
[](https://skillshield.io/report/a6c4107467c6c247)
Powered by SkillShield