ClawHub
Back to skill

Security audit

Web Researcher

Security checks for vulnerabilities and agentic risk

Overview

This is a simple web-research formatting skill that asks the agent to search, fetch sources, summarize, and cite them, with no code execution, persistence, credential access, or hidden behavior.

Install this if you want a structured web-research workflow. Be aware it may trigger on broad research-related wording and will encourage external web browsing and source fetching, so users should still review cited sources and avoid sending sensitive private data into research queries.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
94% confidence
Finding

The activation guidance uses broad, common phrases like 'the latest,' 'news,' or 'research,' which can cause the skill to trigger in many ordinary conversations where explicit web research is not needed. This increases the chance of unintended invocation, unnecessary external browsing, and expanded exposure to untrusted web content.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The instruction to always start with a specific English header, "Jupiter Research Brief," imposes a language-specific output convention. The file does not indicate that this is optional, user-selected, or justified by a documented locale-specific requirement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.