ClawHub
Back to skill

Security audit

Claude

Security checks for vulnerabilities and agentic risk

Overview

This skill is a document-analysis helper with broad activation phrases, but it does not request tools, credentials, persistence, or hidden access.

Before installing, understand that this skill may activate on ordinary contract, memo, or long-document analysis requests. Use it for analytical support only, and do not treat its output as legal, tax, compliance, procurement, or contract-approval advice.

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
Confidence
93% confidence
Finding
The trigger list contains broad phrases like 'analyze contract', 'review long document', and 'long context reasoning' that are likely to overlap with ordinary user requests. This can cause unintended auto-invocation of the skill, expanding its reach beyond deliberate use and potentially routing sensitive legal or commercial content into a skill context the user did not explicitly choose.

Static analysis

No suspicious patterns detected.