Security Audit

buildkite-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

buildkite-automation received a trust score of 95/100, 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 Dynamic Tool Discovery with Potential for Excessive Permissions.

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

100%

Dependency Graph

100%

LLM Behavioral Safety

93%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Dynamic Tool Discovery with Potential for Excessive Permissions The skill instructs the LLM to dynamically discover and execute tools via `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL`. The specific capabilities and permissions of these tools are not hardcoded in the skill but are determined by the Rube MCP configuration and the connected Buildkite account. If the Rube MCP is configured with a Buildkite connection that has overly broad permissions (e.g., administrative access to an entire organization), the LLM, following these instructions, could be led to perform destructive actions (e.g., deleting pipelines, modifying critical settings) or access sensitive data beyond the user's intent. The mention of `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' also suggests a powerful execution environment whose scope is not explicitly defined, potentially leading to broader access than intended. 1. Principle of Least Privilege: Ensure that the Buildkite connection configured within Rube MCP (via `RUBE_MANAGE_CONNECTIONS`) is granted only the minimum necessary permissions required for the intended tasks. 2. User Confirmation: Implement a mechanism for the LLM to seek explicit user confirmation before executing highly sensitive or destructive operations discovered via `RUBE_SEARCH_TOOLS`. 3. Tool Schema Review: Encourage users to carefully review the schemas and capabilities returned by `RUBE_SEARCH_TOOLS` to understand the full scope of actions available. 4. Sandbox `RUBE_REMOTE_WORKBENCH`: If `RUBE_REMOTE_WORKBENCH` allows arbitrary code, ensure it operates within a strictly sandboxed environment with limited access to system resources.	LLM	SKILL.md:40

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/1e87069bb91a5c87.svg)](https://skillshield.io/report/1e87069bb91a5c87)