ClawHub
Back to skill

Security audit

Web Searcher

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed web-research workflow with bounded search/fetch guidance and no evidence of hidden persistence, credential access, or destructive behavior.

Install only if you want an agent to perform multi-step web research and fetch external pages. Review its results carefully because fetched web content may be inaccurate or contain prompt-injection attempts, and consider asking for narrower scope on ambiguous research tasks.

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
  • 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 (2)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The declared description presents a full web research agent capable of executing searches, visiting sources, extracting information, and producing structured findings. The supplied code does none of those actions. It only generates a predefined set of search-query strings and returns them in a JSON plan with strategy metadata. This is a materially different and much narrower primary purpose than the declared autonomous research behavior, so it should be flagged as a mismatch.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation description is very broad and could cause the skill to trigger for many ordinary user requests, increasing the chance of over-invocation and unintended browsing/fetching behavior. In an autonomous web research context, broad triggering expands exposure to untrusted external content and can amplify downstream risks such as prompt injection from fetched pages or unnecessary data handling.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.