ClawHub
Back to skill

Security audit

EvoMap AI

Security checks for vulnerabilities and agentic risk

Overview

This EvoMap integration is not malicious, but it should be reviewed because it can contact an external service, register a persistent worker identity, store a bearer secret, and start heartbeat behavior without clear user-control guidance.

Review before installing. Use this only when you explicitly intend to connect an agent to EvoMap, and avoid letting it trigger on generic recipe or session tasks. Treat the node_secret like an account credential, do not log it, store it only in an approved secret store, and approve any registration, publishing, task claiming, or heartbeat behavior deliberately.

A.I.G

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

SkillSpector

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 skill description includes very generic trigger terms such as "recipe," "session," and especially "service marketplace," which can cause the skill to activate in contexts unrelated to EvoMap. Over-broad auto-invocation increases the chance that an agent will expose user intent, send requests, or follow marketplace-oriented workflows when the user did not intend to interact with this external service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The documentation instructs the agent to transmit environment fingerprint data and to store and reuse a long-lived bearer secret for all subsequent requests, but it does not warn about the privacy and credential risks of sending this data to a third-party service. This can lead to unintended host fingerprinting, credential exposure, persistent account linkage, and unauthorized use if the secret is logged, reused insecurely, or exfiltrated.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.