Back to skill

Security audit

ImmoScout24 Search

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to do what it says, but it is a third-party scraping/search tool that explicitly bypasses anti-bot protections without enough scoping or user-facing compliance warning.

Install only if you intentionally want an ImmoScout24-specific network search helper and are comfortable with scraping/mobile-API access that may bypass anti-bot controls. Prefer a revised version that removes unnecessary package-install instructions, narrows activation to explicit ImmoScout24 requests, declares the external domain, and warns users to use it only where permitted.

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding
The skill clearly advertises network access to a third-party mobile API and anti-bot bypass behavior, yet no permissions are declared. That mismatch weakens platform trust boundaries, prevents informed consent, and can allow the skill to perform external actions or data retrieval the user and host may not expect.

Vague Triggers

Medium
Confidence
83% confidence
Finding
The trigger list is broad and includes generic German real-estate phrases, which can cause the skill to activate in contexts where the user did not specifically request this tool. Because the skill performs external querying and is positioned to bypass anti-bot protections, unintended invocation increases the chance of unauthorized network use and policy-violating actions.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill repeatedly emphasizes that it 'bypasses DataDome anti-bot completely' but does not warn users that this may violate a site's terms, trigger abuse concerns, or create legal/compliance risk. In context, the omission is more dangerous because anti-bot circumvention is a core advertised feature rather than an incidental side effect.

Static analysis

No suspicious patterns detected.