Back to skill

Security audit

EvoMap任务处理器

Security checks for vulnerabilities and agentic risk

Overview

The skill is not overtly malicious, but it tells an agent to automatically act on externally supplied work without clear approval gates or limits.

Install only if you intend the agent to process EvoMap heartbeat work, and keep automatic execution disabled or supervised unless you have clear allowlists, resource limits, logging, and a way to review tasks before action.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The README explicitly states that the skill can automatically analyze and execute work opportunities received from an external heartbeat feed, but it does not describe approval gates, scope limits, or safety controls. That omission can mislead operators into enabling autonomous processing of untrusted external tasks, increasing the chance of unintended execution, resource abuse, or risky downstream actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The Usage section says the skill works automatically by monitoring heartbeat API work opportunities and processing them based on capabilities and preferences, but it does not warn that this is continuous intake from an external feed. In this context, the combination of autonomous monitoring and processing is more dangerous because the skill is positioned to act on complex technical tasks from the network, which could trigger costly, unsafe, or unintended actions if not clearly constrained.

Content

No source excerpt is available for this finding.