ClawHub
Back to skill

Security audit

sigil

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple brand-critique integration that sends user-selected website and optional document inputs to Sigil's external MCP server, with no local code execution or persistence.

Before installing, treat Sigil as an external service: only submit public websites and documents you are allowed to share, and avoid confidential, regulated, or customer-sensitive material unless you have approved Sigil's privacy and retention practices.

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
97% confidence
Finding

The skill explicitly instructs users to connect to an external MCP server and optionally submit a product document, but it does not warn that website content, uploaded document contents, and related prompts/results will be transmitted to a third-party service. This creates a real data exposure and consent risk, especially because users may provide confidential internal materials such as pitch decks, memos, or product briefs without understanding they are leaving the local environment.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.