Security Audit
cabinpanda-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
cabinpanda-automation received a trust score of 89/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 0 high, 2 medium, and 0 low severity. Key findings include Broad tool execution via Rube MCP, Unpinned Rube MCP dependency.
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 | Broad tool execution via Rube MCP The skill allows execution of any discovered Cabinpanda tool via `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` (which includes `run_composio_tool()`). This grants the LLM access to the full range of operations provided by the Cabinpanda toolkit through Rube. If the Cabinpanda toolkit has sensitive capabilities (e.g., data modification, access to PII, financial transactions), an attacker could potentially leverage prompt injection to the LLM to perform unauthorized actions by manipulating the tool calls. The skill itself does not restrict the scope of Cabinpanda operations. Implement stricter access controls or a whitelist of allowed Cabinpanda tools/operations if the full toolkit is not required. Ensure the LLM's interaction with these tools is carefully constrained and validated to prevent unauthorized actions. | LLM | SKILL.md:60 | |
| MEDIUM | Unpinned Rube MCP dependency The skill's manifest declares a dependency on the 'rube' Meta-Capability Provider (MCP) without specifying a version. This means the skill could be used with any version of Rube, potentially leading to unexpected behavior, compatibility issues, or security vulnerabilities if a future version of Rube introduces breaking changes or known exploits. While the `SKILL.md` mentions a specific URL (`https://rube.app/mcp`), the manifest itself does not pin the version. Pin the Rube MCP dependency to a specific, known-good version or a version range in the manifest to ensure stability and security. For example, `"mcp": ["rube@1.2.3"]` or `"mcp": ["rube@^1.0.0"]`. | LLM | manifest.json:1 |
Scan History
Embed Code
[](https://skillshield.io/report/4f2e7ba1b374ddc8)
Powered by SkillShield