ClawHub
Back to skill

Security audit

Web Crawler Engine Free

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only skill for web and community-message archiving whose sensitive behavior is mostly disclosed and purpose-aligned, though users should handle private messages and export/delete actions carefully.

Use this skill only for sites and communities you are authorized to archive. Avoid collecting private messages unless there is clear consent, keep bot tokens in environment variables, and manually review any export, retention, or delete command before running it.

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill's invocation guidance says to use it for database operations, SQL queries, and data storage management generally, even though the actual scope is a narrow web/community archiving tool. Overbroad matching can route unrelated database tasks into a skill that exposes exec and write capabilities, increasing the chance of unsafe command execution or inappropriate data handling outside intended boundaries.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill prominently offers community message archiving and local storage, potentially including private messages and user identifiers, but does not present an upfront privacy warning in the top-level description. This can normalize collection and retention of sensitive content without ensuring users understand consent, retention, and disclosure risks before use.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The free-edition manifest advertises a limited scope, but the documentation simultaneously claims support for export operations. Such scope confusion can cause policy bypass at the orchestration layer, where an agent may allow sensitive data extraction because the skill appears low-risk or limited while still documenting exfiltration-capable behavior.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The free-edition manifest advertises a limited scope, but the documentation simultaneously claims support for export operations. Such scope confusion can cause policy bypass at the orchestration layer, where an agent may allow sensitive data extraction because the skill appears low-risk or limited while still documenting exfiltration-capable behavior.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The documentation frames archived data as read-only for safety, yet later advises deleting expired data from the main database. Contradictory guidance around immutability versus deletion weakens operator expectations and can lead an agent to perform destructive maintenance actions against local archives containing valuable or sensitive records.

Content

No source excerpt is available for this finding.