ClawHub
Back to skill

Security audit

Last 30 Days Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed research helper that searches recent public web/community sources and produces a structured sentiment report.

Installers should expect the skill to perform multiple web searches and include public source links in its output. It should not need access to private accounts, local files, credentials, or persistent memory for its stated purpose.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The phrase "What's the current vibe on Supabase?" is informal and broad, without explicitly indicating the last-30-days window or the cross-platform research behavior. This makes it unclear when the skill should activate versus when a general conversational answer might be intended.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The trigger phrase "Give me a signal report on [product]" is generic and lacks domain-specific constraints. Because it resembles ordinary user requests rather than a narrowly scoped invocation phrase, it could cause unintended activation in normal conversation.

Content

No source excerpt is available for this finding.