Back to skill

Security audit

buyback-screen

Security checks for vulnerabilities and agentic risk

Overview

This skill fetches public Eastmoney A-share buyback data, filters it, and writes a local TSV report in a way that matches its stated purpose.

Install this if you are comfortable with a skill that contacts Eastmoney public data endpoints and writes a TSV report file locally. Review the output path when using --out, especially in shared directories, and treat the generated stock screen as market data rather than financial 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
  • 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 (2)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill explicitly requires network access to Eastmoney and writes TSV output files, but it does not declare any tool scope, permissions, or allowed-tools boundaries. This creates an avoidable over-privilege and transparency problem: an agent may invoke network and file-write capabilities without the user or platform having an explicit least-privilege contract for the skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest description and usage guidance are written entirely in Chinese and present Chinese-language interaction/output as the default behavior, without offering the user a language or locale choice. Under the policy, forcing a specific language without opt-in is a natural-language locale violation unless the constraint is explicitly documented and justified as region-specific.

Content

No source excerpt is available for this finding.