ClawHub
Back to skill

Security audit

Scrappa MCP

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed connector to Scrappa's external MCP search and scraping service, with no hidden code or destructive behavior found.

Before installing, treat this as a remote data connector: Scrappa receives the API-authenticated requests you send through it. Avoid submitting confidential business data, private URLs, sensitive personal information, or third-party profile lookups unless you are comfortable with Scrappa and the relevant downstream services processing that data.

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
95% confidence
Finding

The skill exposes broad access to many third-party data sources, including privacy-sensitive services such as LinkedIn, Google Maps reviews, business profiles, and travel searches, but it provides no warning to users about sending queries, identifiers, URLs, or personal data to an external MCP server. This increases the risk of unintended disclosure of sensitive user or third-party information because users may reasonably assume the skill behaves like a local capability rather than a remote data broker.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.