ClawHub
Back to skill

Security audit

B2B SaaS ABM Campaign

Security checks for vulnerabilities and agentic risk

Overview

This is a plain ABM planning guide with no code, persistence, hidden tool use, or unrelated data handling.

Before installing, users should understand this skill is meant to help plan ABM outreach and may prompt for business targeting details and contact fields. Provide only account, contact, and sales data you are authorized to use, and review any generated outreach for privacy, consent, and marketing compliance before sending.

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
95% confidence
Finding

The trigger condition includes a broad catch-all phrase: 'any request involving a coordinated marketing + sales motion targeting a defined list of accounts.' This can cause the skill to activate for loosely related requests beyond explicit ABM intent, leading to misrouting, over-collection of sales/marketing context, or application of account-targeting playbooks when the user did not ask for ABM-specific guidance.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.