Back to skill

Security audit

Groundapi Anomaly Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed A-share market anomaly reporting helper that uses a GroundAPI MCP service for public market data and does not show hidden execution, persistence, or destructive behavior.

Install only if you are comfortable sending market-analysis queries to GroundAPI through its MCP endpoint. Configure the API key via environment or secret management, avoid committing real keys, and treat outputs as informational market data rather than investment advice.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger conditions are broad and map to common, natural market-chat phrases, which can cause the skill to activate when the user did not explicitly intend to use this external-data workflow. Unintended activation can lead to unnecessary third-party data access, surprising behavior, and over-broad delegation to an MCP server in routine conversation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill includes a realistic API key value directly in the configuration example without a prominent warning that it is a placeholder and must never be hardcoded, shared, or committed. This normalizes unsafe secret-handling practices and increases the chance that users copy the pattern into real deployments, exposing credentials to logs, repositories, or downstream consumers.

Content

No source excerpt is available for this finding.