ClawHub
Back to skill

Security audit

New Relic CLI Skills

Security checks for vulnerabilities and agentic risk

Overview

This New Relic skill is mostly coherent, but it gives agents operational write/delete guidance for alerts without enough guardrails for production use.

Review this before installing in a production New Relic account. Use the narrowest New Relic user key and account access available, prefer read-only use unless you need writes, and require human confirmation before running alert creation/deletion or deployment-marker commands.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
84% confidence
Finding
The skill clearly enables network-capable operations through the New Relic CLI and documents both read and write workflows against the New Relic API, but it does not declare an explicit tool scope such as allowed-tools or permissions. Without a declared scope, an agent runtime may grant broader-than-intended command or network access, increasing the chance of unauthorized API calls, data exfiltration, or unreviewed state-changing actions like alert or deployment modifications.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill documents a destructive command that deletes an alert condition without any warning about irreversible changes, validation steps, or guidance to confirm the target ID before execution. In an operational CLI skill for observability and alerting, this can lead to accidental removal of production monitoring coverage, causing missed incidents or delayed detection of outages.

Static analysis

Detected: suspicious.generated_source_template_injection

User-controlled placeholder is embedded directly into generated source code.

Critical
Code
suspicious.generated_source_template_injection
Location
deployments/SKILL.md:52