ClawHub
Back to skill

Security audit

Unofficial Urban Dictionary API

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward helper for querying an external slang dictionary API, with its network use disclosed and no evidence of persistence, credential access, or hidden behavior.

Install this if you are comfortable sending slang lookup terms and related query parameters to unofficialurbandictionaryapi.com. Results may contain offensive or NSFW content, which the skill explicitly notes.

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
  • 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)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill instructs the agent to make outbound HTTP requests to an external API and to run a helper script, but it does not declare any explicit tool scope such as allowed tools or network permissions. This weakens policy enforcement and reviewability because the agent may be granted broader capabilities than the skill metadata makes clear, increasing the chance of unintended network access or misuse in environments that rely on manifest-level restrictions.

Content

No source excerpt is available for this finding.