Back to skill

Security audit

Local Web Search

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward DuckDuckGo search helper whose network behavior is disclosed and limited to user-provided searches.

Install only if you are comfortable with your search terms being sent to DuckDuckGo through HTML scraping. The skill does not show credential access, persistence, or local data exfiltration, but it should not be used for secret or sensitive queries.

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
Vulnerability Patterns
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill invokes a local script that performs outbound web requests, but the manifest does not declare any tool scope such as allowed network access. This creates a permission-transparency gap: reviewers and policy enforcers cannot reliably determine from the skill definition that network activity will occur, increasing the risk of unexpected data egress or misuse in constrained environments.

Static analysis

No suspicious patterns detected.