Security Audit

diffbot-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

diffbot-automation received a trust score of 85/100, 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 Potential for generic remote code execution via RUBE_REMOTE_WORKBENCH.

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

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

85%

Behavioral Risk Signals

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential for generic remote code execution via RUBE_REMOTE_WORKBENCH The skill documentation instructs the LLM to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This tool appears to be a generic execution mechanism. If `run_composio_tool()` can execute arbitrary code, shell commands, or any Composio tool without proper sandboxing, input validation, or strict access controls, it creates a path for command injection, data exfiltration, and excessive permissions. A malicious user could craft prompts to manipulate the LLM into passing dangerous arguments to this tool, leading to unauthorized actions, access to sensitive data (e.g., files, environment variables), or execution of arbitrary code on the underlying Rube MCP system. Clarify the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Specify what types of operations are allowed and what security measures are in place (e.g., sandboxing, strict input validation, allowed tool lists, restricted execution environment). If it allows arbitrary code execution, consider removing or severely restricting its use to prevent misuse.	LLM	SKILL.md:68

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/c054dbc51df84846.svg)](https://skillshield.io/report/c054dbc51df84846)