ClawHub
Back to skill

Security audit

B2B SaaS ICP Builder

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward ICP/persona planning skill with no code execution, persistence, credential use, or hidden data movement.

Before installing, expect this skill to help structure ICP and buyer persona work. Be mindful that it may activate during adjacent go-to-market planning conversations, and only provide CRM or customer details you are comfortable sharing in the chat.

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 description expands activation beyond the specific example phrases to 'any request to understand, document, or sharpen' the company's best customers and also when the user is 'starting go-to-market planning' or 'not sure who to focus on.' These conditions are broad and ambiguous, overlapping with many general strategy conversations rather than a narrowly scoped ICP-building request.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.