ClawHub
Back to skill

Security audit

Web Trim

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches and summarizes user-requested web pages in a short-lived worker, with no evidence of hidden persistence, credential access, or destructive behavior.

Install only if you are comfortable with the agent fetching web pages you ask it to research or summarize. Avoid using it on private, internal, or sensitive URLs unless you understand how the web_fetch tool handles access and data exposure.

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
96% confidence
Finding

The activation condition "When asked to 'Research' or 'Summarize' a site" is broad and underspecified, so the skill may trigger in contexts the user did not explicitly intend. That can cause unreviewed external fetching and summarization of arbitrary URLs, increasing the chance of misuse, prompt-routing errors, or processing untrusted content without sufficient constraints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.