Back to skill

Security audit

Gold Price Report

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public gold, silver, brand, and related futures prices from a disclosed quote API without persistence, credential use, or hidden behavior.

Install this if you are comfortable with the skill contacting api-gold.aibuy.cloud for live quote data. Treat the prices as third-party market data, and be aware that it may answer in Chinese by default and includes one copper futures quote alongside precious-metals data.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill invokes a bundled Python script that fetches real-time quotes from an external source, which implies network access, but the manifest does not declare any tool scope or permissions. This creates a transparency and policy-enforcement gap: an agent or reviewer cannot easily determine that external connectivity is required, and a broader runtime may permit undeclared outbound requests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instruction 'Summarize in plain Chinese unless the user asks for raw data only' imposes a default language choice rather than letting the user choose their preferred language. This is a natural-language policy concern because it forces a locale/language behavior without explicit opt-in or an offered alternative.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest describes a gold/silver price lookup and precious-metals market brief, with examples limited to gold, silver, and precious-metals futures. Including 沪铜 (copper) adds a commodity outside that stated purpose, which is not justified by the described skill scope.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.