ClawHub
Back to skill

Security audit

LinkFox

Security checks across malware telemetry and agentic risk

Overview

This LinkFox skill is a disclosed connector for reading and reporting on LinkFox-connected commerce data, with some normal account-connection setup risk.

Install this only if you expect the agent to use your OOMOL-connected LinkFox account to retrieve commerce, ads, store, order, campaign, and report data. Review the oo CLI installer before first-time setup, and require explicit confirmation before any future LinkFox action that is tagged write or destructive or could change account state.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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 (3)

Description-Behavior Mismatch

Medium
Confidence
95% confidence
Finding
The manifest and description present the skill as only for 'searching and reading data', but the body documents authorization flows and actions that may change external state. This mismatch can mislead an agent or user into invoking the skill under a lower-risk assumption, reducing appropriate confirmation for non-read operations.

Description-Behavior Mismatch

Medium
Confidence
92% confidence
Finding
The Safety section explicitly acknowledges write/destructive operations, confirming that the skill's top-level description is incomplete and potentially misleading. In agentic use, this inconsistency can cause the skill to be selected for tasks presumed safe while still exposing higher-risk operations and auth flows.

Vague Triggers

Medium
Confidence
88% confidence
Finding
The instruction to use this skill for 'ANY LinkFox request' is overly broad and can cause aggressive routing whenever LinkFox is mentioned, even when the user did not request connector use or when a safer/narrower path exists. Because the skill also includes non-read capabilities and authorization-related actions, over-selection increases the chance of unnecessary data exposure or unintended side effects.

VirusTotal

61/61 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.