Security Audit

brightdata-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

brightdata-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 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Generic Tool Execution via Rube MCP allows broad access.

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

Manifest Analysis

100%

Static Code Analysis

93%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Generic Tool Execution via Rube MCP allows broad access The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which are generic mechanisms to execute any tool exposed by Rube MCP. While the skill's stated purpose is 'Brightdata Automation', these tools do not inherently restrict execution to Brightdata-specific operations. If Rube MCP is configured to expose tools with broad system access (e.g., filesystem access, arbitrary network requests, shell commands), this skill could be used by a compromised LLM to invoke them, potentially leading to excessive permissions beyond the intended scope of Brightdata operations. 1. Restrict Rube MCP's exposed tools: Ensure Rube MCP only exposes tools strictly necessary for Brightdata operations and that these tools have minimal required permissions. 2. Implement LLM-side guardrails: Add explicit guardrails within the LLM's system instructions to limit the types of tools it can execute via `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to only those relevant to Brightdata. 3. Refine skill instructions: If possible, refine the skill's instructions to explicitly emphasize that only Brightdata-specific tools should be executed, or provide examples that implicitly guide the LLM towards this.	Static	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/6118be69e5776e3c.svg)](https://skillshield.io/report/6118be69e5776e3c)