ClawHub
Back to skill

Security audit

Geo Metrics Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is an advisory GEO monitoring design helper and does not show hidden execution, credential handling, data exfiltration, or destructive behavior.

Install this if you want help designing GEO metrics dashboards, schemas, alerts, and runbooks. Review any generated pseudo-configurations before implementing them in BI, alerting, or data systems, and provide credentials or live system access only through your normal approved workflows.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The declared description presents this skill as an operational monitoring/orchestration system for continuously tracking GEO metrics over time and reacting to changes. However, the supplied code does not implement monitoring, data ingestion, visualization, alerting, anomaly detection, scheduling, or orchestration. It only defines a few default metric definitions, formats them into markdown tables, and outputs a documentation snippet describing a metrics catalog and example schema. While the subject matter is related to GEO metrics, the actual code's primary purpose is static schema/document generation, which is materially different from the declared real-time monitoring and alerting functionality.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
86% confidence
Finding

The skill appears capable of producing artifacts such as schemas, dashboard specs, runbooks, and pseudo-configurations that could reasonably lead an agent to write files, but it does not declare any tool scope or allowed tools. In an agent environment, missing explicit permission boundaries can cause the orchestrator to grant broader-than-intended file write behavior, increasing the risk of unauthorized workspace modification or persistence of generated content.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger rule instructs invocation whenever the user's general intent appears related, and explicitly says not to limit triggering to exact keywords. Overly broad routing can cause this skill to activate in situations where a narrower or safer skill would be more appropriate, increasing the chance of unnecessary orchestration, unintended data handling, or tool use in loosely related conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.