ClawHub
Back to skill

Security audit

测试 skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small, coherent wrapper for a summarization CLI, with external AI and extraction services disclosed enough to fit its purpose.

Before installing, confirm you trust the Homebrew tap and the summarize CLI. Treat any URL or local file you summarize as potentially sent to the selected AI provider, and to Firecrawl or Apify when those fallback options are enabled.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill explicitly instructs users to summarize URLs, local files, PDFs, images, audio, and YouTube content using third-party AI providers and optional extraction services, but it does not warn that submitted content may be transmitted off-device to external services. This can cause unintentional disclosure of sensitive local file contents, private URLs, or regulated data, especially because optional fallbacks like Firecrawl and Apify further expand the set of external recipients.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.