ClawHub
Back to skill

Security audit

Hotmention

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed lead-search helper that uses normal web search or an optional HotMention API key, with no hidden code or destructive behavior found.

Before installing, be aware that product keywords and lead-search terms may be sent to web search or, if you configure HOTMENTION_API_KEY, to HotMention. Use the paid API only if that sharing is acceptable, and treat any automated monitoring such as cron as a separate setup choice you control.

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
94% confidence
Finding

The trigger phrase "When the user asks to find mentions, leads, or buying intent for their product" is broad and loosely scoped, which can cause the skill to activate for a wide range of generic marketing or research requests. This increases the chance of unintended invocation and unnecessary external searching or API use, especially in agent environments where multiple skills may compete for ambiguous requests.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.