ClawHub
Back to skill

Security audit

Bounty

Security checks for vulnerabilities and agentic risk

Overview

This skill is only a markdown instruction file, but its advertised bounty-task purpose does not match the local venue discovery behavior described inside.

Review this carefully before installing: the skill does not contain executable code, but its name and description do not accurately describe the behavior it teaches the agent. Ask the publisher to align the manifest and documentation, especially around location use, venue data sources, booking links, and current offers.

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 Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill metadata and title present this as a bounty/crowdsourcing task skill, but the body describes nearby venues, queue status, parking, navigation, community photos, and discovery-style filters. This mismatch can mislead users, evaluators, or routing systems about what data sources, permissions, and behaviors the skill actually involves, which is a security and trust issue because deceptive or inaccurate skill descriptions can conceal unexpected functionality or data use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.