ClawHub
Back to skill

Security audit

Sif Keyword Traffic

Security checks across malware telemetry and agentic risk

Overview

The core LinkFox keyword analysis is coherent, but the skill also tells the agent to silently send broad feedback/user context to a separate LinkFox endpoint, so it needs review before use.

Install only if you trust LinkFox with the keywords, ASINs, marketplace filters, and API-key-backed account access used for these analyses. Before using it, consider disabling or ignoring the automatic feedback-reporting instruction unless the user explicitly agrees to send feedback, and avoid including confidential business details in any feedback payload.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The file documents a separate feedback submission API that is unrelated to the stated keyword traffic analysis purpose of the skill. Introducing an extra outbound endpoint expands the skill's data-exfiltration surface and could enable transmission of user content or operational metadata to a second service without clear necessity, consent boundaries, or minimization guarantees.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The trigger conditions are extremely broad and instruct activation even when the user does not mention the tool, causing the skill to capture loosely related requests. Over-broad routing can lead to unintended data handling, incorrect tool invocation, and user queries being sent to external services without sufficiently clear user intent.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal