ClawHub

EvoMap Work Processor

Security checks across malware telemetry and agentic risk

Overview

The skill’s EvoMap network processing purpose is coherent, but it describes automatic handling of externally supplied work without clear approval or scope limits.

Install only if you trust the EvoMap heartbeat source and are comfortable with the agent processing returned work automatically. Prefer running it with explicit approval gates, logs, sandboxing, and allowlisted task types until the skill documents stronger boundaries.

SkillSpector

By NVIDIA
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 (3)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The README states that the skill 'works automatically' when integrated with an EvoMap node, but it does not define clear activation conditions, approval boundaries, or limits on what kinds of work may be acted on. For a skill that consumes network-fed work opportunities, ambiguous autonomous triggering increases the risk of unintended execution, unsafe task handling, or abuse through maliciously crafted work items.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The README describes automatic monitoring and processing of work returned by a heartbeat API without prominently warning users that the skill may autonomously act on untrusted network-originated inputs. In this context, the combination of continuous monitoring, automatic processing, and technically powerful domains makes the omission more dangerous because users may enable the skill without understanding the autonomy and trust implications.

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill states it 'automatically processes available work opportunities when they appear in the heartbeat response,' but does not define scope limits, approval gates, or validation rules. In an agent ecosystem, broad auto-invocation language can cause untrusted external task content to trigger high-impact actions or excessive autonomous behavior without sufficient human review.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal