ClawHub
Back to skill

Security audit

B2B SaaS Campaign Brief

Security checks for vulnerabilities and agentic risk

Overview

This is a simple campaign brief template skill with no code execution, credential access, persistence, or hidden data handling.

Installers should expect this skill to help draft structured marketing campaign briefs. Review whether the broad campaign-planning trigger overlaps with other marketing skills in your setup, but no sensitive or high-impact behavior was found.

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 trigger description is broad enough to match many generic marketing-planning requests, which can cause the agent to invoke this skill when a more appropriate or narrower skill should handle the task. Over-broad routing is a security and reliability concern because it increases the attack surface for prompt injection, data misrouting, and unintended tool selection in multi-skill environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.