ClawHub
Back to skill

Security audit

eonik companion

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed eonik marketing companion skill that reads and saves eonik workspace context for briefs and research, with no code execution or ad-spend authority.

Install this only if you intend your agent to use your connected eonik workspace for marketing research and brief drafting. Review before allowing it to save durable brand notes or plans, and avoid letting the host apply it to generic marketing conversations where eonik data should not be used.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The activation condition includes broad natural-language triggers like when the user asks about their ads, competitors, brand, or what to make next, which can match many ordinary marketing conversations even when the eonik tool context is not intended. This can cause the skill to activate outside its narrow scope and steer the agent into using workspace-connected tools or brand-specific guidance in situations where the user only wanted general advice, increasing the risk of unintended data access or tool use.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.