ClawHub
Back to skill

Security audit

Enterprise Ai Knowledge

Security checks for vulnerabilities and agentic risk

Overview

This skill is a static enterprise AI knowledge guide with no code execution, data access, persistence, or hidden behavior.

Before installing, expect this skill to influence answers for a fairly broad range of enterprise AI planning questions. It appears safe as an advisory knowledge skill, but users should treat its business claims and statistics as guidance to verify rather than authoritative facts.

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 skill says it takes any 'enterprise AI related question' and lists broad 'trigger scenarios' such as strategy consulting, implementation evaluation, team planning, vendor selection, and project kickoff. This lacks clear boundaries or exclusion conditions, so the skill could match a wide range of ordinary business discussion rather than a narrowly defined invocation context.

Content

No source excerpt is available for this finding.