ClawHub
Back to skill

Security audit

Marketing Orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown-only marketing audit orchestrator whose external-service use is expected for its stated purpose, with no hidden execution or persistence found.

Before installing, confirm you are comfortable with the marketing handles/domains and resulting audit data being passed to multiple collector skills and external marketing services configured in your environment. Treat configured API keys as sensitive and verify the actual collector skills separately.

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • 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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown file describes orchestrating multiple collector skills and explicitly mentions handling API keys and environment variables for external services, but it does not include any user-facing warning about privacy, external data transmission, or credential-sensitive behavior. For a markdown skill description, the absence of such disclosure can leave users unaware that their inputs may be sent across multiple sub-skills and third-party services.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill documentation explicitly says collector errors should not block orchestration, but the pseudocode performs sequential awaited sub-skill calls with no try/catch or fallback handling. In practice, any collector failure would terminate the workflow early, creating a denial-of-service condition for the overall audit pipeline and making the orchestrator less resilient to failures in external dependencies.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.