ClawHub
Back to skill

Security audit

B2B SaaS Positioning & Messaging

Security checks for vulnerabilities and agentic risk

Overview

This is a simple B2B SaaS messaging worksheet skill with no executable code or privileged behavior.

This skill appears safe for positioning and messaging work. Be aware it may activate for a wide range of company/product writing requests, so users who want narrower behavior may prefer tighter trigger wording, but no dangerous runtime 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
93% confidence
Finding

The manifest says to use the skill whenever the user wants to 'define, refine, or document' messaging and even extends this to 'any request to sharpen how the company talks about itself,' which is an expansive natural-language trigger without clear boundaries or exclusions. This can cause unintended invocation because it overlaps with common business-writing requests and does not specify negative examples or narrower activation constraints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.