Security Audit

beaconchain-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

beaconchain-automation received a trust score of 76/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Unpinned dependency in manifest, Potential Arbitrary 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 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

70%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unpinned dependency in manifest The skill manifest specifies a dependency on 'rube' without a version constraint. This allows the system to fetch any version of the Rube MCP, including potentially malicious future versions, which introduces a supply chain risk. It is best practice to pin dependencies to specific, known-good versions. Pin the 'rube' dependency to a specific, known-good version (e.g., `"rube": ["~1.0.0"]` or `"rube": ["1.2.3"]`) in the skill manifest.	LLM	manifest:1
HIGH	Potential Arbitrary Code Execution via RUBE_REMOTE_WORKBENCH The skill instructs the agent to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' and the function name `run_composio_tool()` strongly suggest a capability for executing arbitrary or complex operations, potentially including arbitrary code or shell commands. If the arguments to `run_composio_tool()` can be controlled by untrusted input, this could lead to command injection or arbitrary code execution, granting excessive permissions to the agent. Clarify the exact capabilities and security boundaries of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary code execution, it should be removed or heavily restricted, and its usage should be explicitly documented with security implications. Ensure all inputs to `run_composio_tool()` are strictly validated and sanitized.	LLM	SKILL.md:65

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/33ffd4fc07062ad1.svg)](https://skillshield.io/report/33ffd4fc07062ad1)