Back to skill

Security audit

Money Saving Tips

Security checks for vulnerabilities and agentic risk

Overview

The skill is not executable and shows no malware behavior, but its published finance-savings description does not coherently match the location and venue-discovery instructions inside the skill.

Review this skill carefully before installing because its name and description may cause it to be invoked for personal finance help, while its actual instructions appear to guide location-based venue discovery. It should be clarified or renamed before normal use.

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 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 (3)

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The manifest promises household bill optimization and money-saving guidance, but the body documents a different capability centered on location-based venue discovery, queue status, parking, and navigation. This mismatch is dangerous because users and downstream agents may grant trust, route requests, or supply data under false assumptions, enabling deceptive behavior, inappropriate data collection, or misuse of the skill outside its declared purpose.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The title and description present a personal-finance savings assistant, while the documentation describes a local discovery tool. Materially different intents increase the risk of user deception and policy bypass because the skill can be invoked in contexts where finance advice is expected but location-oriented behavior is actually performed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language description and all user-facing instructions are written exclusively in Chinese, with no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking region. This can violate a language/locale policy when a skill imposes a specific language without user opt-in.

Content

No source excerpt is available for this finding.