ClawHub
Back to skill

Security audit

FindBroadband

Security checks for vulnerabilities and agentic risk

Overview

The scanners classify this skill as benign: they found one privacy concern about sending property details to FindBroadband, while the reported behavior is consistent with property-specific broadband checks.

Before installing, consider whether you are comfortable sharing your postcode and house number or name with FindBroadband for an availability check. The scanners report a privacy transparency issue, not malicious behavior; the verdict is benign.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow sends the user's exact property details to FindBroadband without a user-facing privacy notice.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The workflow directs the assistant to transmit an exact residential address and property identifier to an external service without first telling the user who will receive those details. Property-level broadband checks legitimately require location information, and the skill identifies the provider internally, which reduces suspicion of malicious exfiltration; however, neither ensures the user understands that their address will leave the chat for third-party processing.

Content

No source excerpt is available for this finding.