ClawHub
Back to skill

Security audit

Research Assistant

Security checks for vulnerabilities and agentic risk

Overview

This is a simple web-research helper that tells the agent to search, fetch sources, and write reports, with no hidden code or persistence found.

Before installing, understand that this skill encourages the agent to use external web search and URL fetching for research-style tasks. Avoid using it for sensitive private documents unless you actually want online research involved, and check the cited sources in generated reports.

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
91% confidence
Finding

The skill description includes broad activation conditions such as researching 'any topic,' summarizing documents, comparing alternatives, and gathering competitive intelligence. These phrases can over-match common user requests and cause the agent to invoke this skill in situations where web research is unnecessary or where a narrower, safer skill should apply, increasing the chance of unintended external data access and overbroad task handling.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.