Security Audit

coupa-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

coupa-automation received a trust score of 73/100, 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 Broad Tool Execution Capabilities, Unpinned External MCP Dependency.

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

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution Capabilities The skill allows the LLM to execute any Coupa operation available through the Rube MCP, as discovered by `RUBE_SEARCH_TOOLS` and executed via `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH`. This grants broad, unconstrained access to Coupa functionalities, limited only by the permissions of the connected Coupa account. A malicious prompt could leverage this to perform unauthorized actions within Coupa. Implement granular access controls or a whitelist of allowed Coupa operations. Ensure that the Rube MCP connection to Coupa uses the principle of least privilege. Consider adding a human-in-the-loop approval step for sensitive operations.	LLM	SKILL.md:49
HIGH	Unpinned External MCP Dependency The skill explicitly relies on an external Rube MCP server (`https://rube.app/mcp`) and the `coupa` toolkit without specifying a version or providing integrity checks. This introduces a significant supply chain risk. If the `rube.app` service is compromised, or if the `coupa` toolkit within Rube MCP is maliciously updated, the skill's execution could be hijacked, leading to data exfiltration, unauthorized actions, or other security breaches. Implement version pinning for the Rube MCP and its toolkits if possible. Conduct regular security audits of external dependencies. Consider hosting a trusted, version-controlled instance of the MCP or using a private registry. Implement integrity checks for external resources.	LLM	SKILL.md:17

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/57a7c5973df7203c.svg)](https://skillshield.io/report/57a7c5973df7203c)