Security Audit

rkvst-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

rkvst-automation received a trust score of 83/100, 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, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned Rube MCP dependency, `RUBE_REMOTE_WORKBENCH` allows potentially arbitrary code 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

78%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	`RUBE_REMOTE_WORKBENCH` allows potentially arbitrary code execution The `RUBE_REMOTE_WORKBENCH` tool, particularly when used with `run_composio_tool()`, is described for 'Bulk ops' and implies a powerful execution capability. Without strict sandboxing and input validation, this tool could allow an attacker to execute arbitrary code or perform actions beyond the intended scope of the Rkvst toolkit on the remote workbench. The `SKILL.md` provides no details on the security controls or limitations of `run_composio_tool()`, making it a potential command injection and excessive permissions risk. Implement strict input validation and sandboxing for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that `run_composio_tool()` only executes whitelisted, pre-defined operations and does not allow arbitrary code execution or access to sensitive system resources. Provide clear documentation on the security boundaries and limitations of this tool.	LLM	SKILL.md:80
MEDIUM	Unpinned Rube MCP dependency The skill's manifest specifies a dependency on 'rube' MCP but does not pin it to a specific version. This can lead to unexpected behavior, compatibility issues, or introduce vulnerabilities if a future version of 'rube' contains breaking changes or malicious updates. It is best practice to pin dependencies to a known-good version. Pin the 'rube' MCP dependency to a specific, known-good version in the skill's manifest. For example, '{"requires": {"mcp": ["rube==1.2.3"]}}'.	LLM	SKILL.md

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/40da92138aaf2bb0.svg)](https://skillshield.io/report/40da92138aaf2bb0)