ClawHub
Back to skill

Security audit

web-summarizer

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward web/text summarizer with no install scripts or persistence; the main caveat is broad activation wording.

Install if you want a skill that summarizes web pages or pasted text. Be aware that pages and pasted content may contain sensitive information or prompt-injection text, so use it only with sources you are comfortable having the agent fetch and summarize.

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
Confidence
84% confidence
Finding
The description is broad enough to trigger on a wide range of generic requests involving URLs or pasted text, which can cause the skill to activate outside narrowly intended summarization contexts. Over-broad routing increases the chance that sensitive user-provided content or unrelated web material is sent into this skill unexpectedly, expanding attack surface and enabling prompt-injection exposure from arbitrary pages.

Static analysis

No suspicious patterns detected.