Security Audit

buildkite-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

buildkite-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 Skill enables broad Buildkite automation with potential for command execution.

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

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill enables broad Buildkite automation with potential for command execution The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to perform 'Buildkite operations' and 'Bulk ops'. These tools grant the LLM broad access to the connected Buildkite environment. If the underlying Buildkite tools or `run_composio_tool()` allow for arbitrary script execution, modification of critical CI/CD configurations, or access to sensitive build data, this could lead to command injection, unauthorized code execution, data exfiltration, or significant disruption within the Buildkite pipelines. The skill does not define or limit the scope of operations that can be performed, relying on the discovery of tools via `RUBE_SEARCH_TOOLS`, which implies access to all available Buildkite functionalities through Rube MCP. Implement granular access controls for the Rube MCP connection to Buildkite, ensuring the LLM can only access a minimal set of necessary Buildkite operations. If `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH` can execute arbitrary code, ensure strict input validation and sandboxing for any user-provided arguments. Consider limiting the LLM's ability to discover or execute tools that have high-impact or command-execution capabilities.	LLM	SKILL.md:47

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/43bfafa94e662c68.svg)](https://skillshield.io/report/43bfafa94e662c68)