Security audit

New Relic CLI Skills

Security checks for vulnerabilities and agentic risk

Overview

This New Relic CLI skill is coherent and disclosed, but it requires New Relic API access and includes guided IAM and deployment write workflows.

Install this only where the agent may access your New Relic account. Use a minimally scoped User Key, avoid querying or sharing sensitive log, prompt, response, or customer data unless authorized, and require explicit review before running IAM writes, profile deletion, or deployment marker automation.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill explicitly documents shell command execution via the newrelic CLI and performs networked access to New Relic APIs, but it does not declare a corresponding tool scope such as allowed-tools or permissions. This creates an authorization ambiguity where an agent may be allowed to invoke shell/network-capable actions without an explicit least-privilege contract, increasing the risk of unintended command execution, API access, or write operations such as deployment markers and IAM changes.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The file is titled and described as "Agent Diagnostics" focused on validating agent configuration, connectivity, and reporting status, but the later section documents adding, switching, and deleting CLI profiles. Profile lifecycle management changes persisted authentication/config state and is not part of diagnosing agent health or reporting behavior.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: This markdown file instructs users to run ad-hoc queries and explicitly lists data sources such as Log, ProcessSample, SystemSample, and DatabaseTrace. Because query output may contain sensitive operational details or log content, the skill description should warn users to avoid querying or sharing sensitive data unintentionally.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 82% confidence
Finding: This markdown file includes a destructive operation, newrelic profile delete, but does not explicitly warn the user that it permanently removes a stored profile from local CLI configuration. Although the snippet verifies the exact name before deletion, it lacks a user-facing caution about the impact of the delete action.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.