Security Audit

sourcegraph-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

sourcegraph-automation received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via RUBE_REMOTE_WORKBENCH, Unpinned External Service Dependency (Supply Chain Risk).

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

70%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via RUBE_REMOTE_WORKBENCH The skill documentation suggests using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'workbench' often implies an environment capable of executing arbitrary code or commands. If `run_composio_tool()` allows for the execution of unvalidated or untrusted code/commands, it presents a significant command injection vulnerability. An attacker could potentially craft inputs to execute malicious commands within the Composio environment, leading to system compromise, data exfiltration, or unauthorized actions. Ensure that `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` are strictly sandboxed and only permit execution of pre-approved, safe operations. Implement robust input validation and restrict the capabilities of any executed code. Provide clear documentation on the security implications and limitations of this tool.	LLM	SKILL.md:68
HIGH	Unpinned External Service Dependency (Supply Chain Risk) The skill explicitly instructs users to add `https://rube.app/mcp` as an MCP server. This constitutes an unpinned dependency on an external service. If `rube.app` were to be compromised, or if the service were to serve malicious or altered tools, the LLM using this skill could be directed to execute harmful operations. There is no mechanism described for version pinning or integrity verification of the Rube MCP service, making it vulnerable to supply chain attacks. Implement mechanisms to pin the version of the Rube MCP service or toolkit. Consider using a trusted, internal mirror or a content-addressable system to ensure the integrity and authenticity of the served tools. Provide instructions for verifying the source and integrity of the MCP endpoint.	LLM	SKILL.md:20

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e46e3516638fa7d4.svg)](https://skillshield.io/report/e46e3516638fa7d4)