Back to skill

Security audit

Parallel Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for splitting independent research tasks across parallel agents, with no evidence of hidden code, persistence, credential access, or destructive behavior.

Install this if you want agents to divide clearly independent research questions and later merge the results. Users should be aware it may spawn multiple research agents and the instructions are currently Chinese-only.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The manifest description and all operational instructions are written in Chinese, and the skill does not state that language selection is optional or user-driven. Under the stated policy, forcing a specific language or locale without opt-in is a natural-language policy violation unless the regional restriction is justified.

Content

No source excerpt is available for this finding.