ClawHub
Back to skill

Security audit

Metrics

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local metrics-planning helper with disclosed, opt-in memory and no evidence of hidden execution, network transfer, or destructive behavior.

Before installing, decide whether you want the skill to remember metric decisions in ~/metrics/ and whether it should activate proactively. Avoid storing confidential raw business data, secrets, credentials, or unrelated personal details in its memory file.

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
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The setup instructs the skill to activate whenever the user discusses broad topics like KPIs, dashboards, formulas, tracking, or reporting, which creates an overly expansive trigger surface. This can cause the skill to engage in contexts the user did not explicitly intend, increasing the chance of unsolicited persistence, cross-context interference, or collection of business-sensitive measurement details.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.