ClawHub
Back to skill

Security audit

Marketing Tool

Security checks for vulnerabilities and agentic risk

Overview

This looks like a real marketing API skill, but it needs review because it can create and research prospects, create campaigns, incur paid API calls, and expose agent conversation logs without privacy or control details.

Review this before installing in any environment that may handle customer, prospect, confidential, or regulated data. Configure explicit human approval for creating prospects or campaigns and for any paid x402 requests, and avoid sending secrets or sensitive conversation content unless the provider's retention, access, and deletion practices are acceptable.

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
  • 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
95% confidence
Finding

The metadata and description advertise 'agent conversation logs' and a /api/marketing/conversations endpoint, but provide no warning that potentially sensitive prompts, customer data, or operational details may be stored and later accessed. This can cause users or calling agents to transmit confidential information under the false assumption that interactions are transient, creating avoidable privacy and confidentiality exposure.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly enables prospect research, campaign enrollment, outreach tracking, and marketing spend monitoring, all of which can involve collection and processing of personal or behavioral data. Omitting clear privacy and consent warnings increases the risk that downstream agents or users will use the skill for surveillance-like lead profiling or outreach without understanding legal and ethical constraints.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.