Security Audit

grafbase-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

grafbase-automation received a trust score of 80/100, 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, Broad access to Grafbase operations via Rube MCP.

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	Unpinned Rube MCP dependency The skill manifest specifies a dependency on the 'rube' MCP without a version constraint. This means the skill will always use the latest version of Rube MCP, which could introduce breaking changes, unexpected behavior, or security vulnerabilities if the upstream service changes without explicit review or update to this skill. This creates a supply chain risk. Pin the Rube MCP dependency to a specific version or version range (e.g., `{"mcp": ["rube@^1.0.0"]}`) in the skill's manifest to ensure stability and mitigate supply chain risks.	LLM	SKILL.md:1
MEDIUM	Broad access to Grafbase operations via Rube MCP The skill provides the LLM with access to powerful Rube MCP tools like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. These tools allow for the execution of any discovered Grafbase operation or Composio tool, granting broad, unrestricted access to Grafbase resources and operations that the connected Rube account has permissions for. If the LLM is compromised (e.g., via prompt injection), it could be instructed to perform unauthorized or destructive actions on Grafbase, leveraging these broad capabilities. Consider if the skill's functionality can be narrowed to specific Grafbase operations rather than providing general-purpose execution. If broad access is necessary, ensure robust input validation and authorization mechanisms are in place within the Rube MCP and Grafbase. Implement strict LLM guardrails to prevent malicious use of these powerful tools.	LLM	SKILL.md:59

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/25201fdab393a4da.svg)](https://skillshield.io/report/25201fdab393a4da)