Security Audit

new_relic-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

new_relic-automation received a trust score of 85/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Generic Tool Execution Allows Broad Access.

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

93%

Behavioral Risk Signals

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Generic Tool Execution Allows Broad Access The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which are generic mechanisms for executing any tool available via the Rube MCP and Composio ecosystem. While the skill's stated purpose is New Relic automation, these tools do not inherently restrict execution to New Relic-specific operations. If the underlying Rube MCP or Composio platform exposes tools with broad system access (e.g., file system, network, arbitrary code execution), this skill implicitly grants the LLM the ability to invoke such tools, potentially leading to excessive permissions beyond its intended scope. An attacker could craft a prompt injection to guide the LLM to discover and execute a non-New Relic tool with sensitive capabilities. Implement stricter access controls or a whitelist of allowed tool slugs for this specific skill when using generic execution tools like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. Ensure the LLM orchestrator enforces these restrictions. Alternatively, the skill documentation should explicitly state that only New Relic tools should be executed and provide guidance on how to enforce this.	LLM	SKILL.md:70

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/2896da553625cddc.svg)](https://skillshield.io/report/2896da553625cddc)