ClawHub
Back to skill

Security audit

Invoice Management Faq

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward invoice-process FAQ with no evidence of hidden behavior, credential use, persistence, network access, or data mutation.

Installers should treat this as an internal invoice-policy reference, not as a live finance system. Verify the bundled FAQ matches current company policy before relying on it, especially because the skill instructs agents not to modify the source answer text.

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 phrases are generic invoice-related terms that can match ordinary conversation without a clear boundary for when the skill should activate. This can cause unintended invocation and make the agent answer from a rigid FAQ in contexts where a broader, more accurate, or policy-aware response is needed.

Static analysis

No suspicious patterns detected.