Security Audit
codeinterpreter-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
codeinterpreter-automation received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Inherent Command Injection and Excessive Permissions Risk via Code Interpreter Tool.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Inherent Command Injection and Excessive Permissions Risk via Code Interpreter Tool The skill's primary purpose is to automate tasks using a 'codeinterpreter' tool via Composio's Rube MCP. By its nature, a code interpreter executes code. If the arguments passed to the `RUBE_MULTI_EXECUTE_TOOL` for the `codeinterpreter` toolkit are not rigorously validated and sanitized against malicious input, or if the underlying `codeinterpreter` execution environment is not securely sandboxed with minimal necessary permissions, a malicious user could leverage this skill to inject arbitrary code or commands (Command Injection). This could lead to unauthorized execution, data exfiltration, or access to sensitive system resources (Excessive Permissions). The skill documentation provides the interface for the LLM to call these tools, making the security of the underlying `codeinterpreter` implementation critical. Ensure the `codeinterpreter` tool within Composio's Rube MCP is executed in a strictly sandboxed environment with robust input validation and sanitization for all arguments. The sandbox must enforce least privilege, restricting filesystem access, network access, and process execution to only what is absolutely necessary for legitimate `codeinterpreter` tasks. Implement comprehensive logging and monitoring of all `codeinterpreter` activities. | LLM | SKILL.md:60 |
Scan History
Embed Code
[](https://skillshield.io/report/6b7a2a84a05b5bf1)
Powered by SkillShield