ClawHub
Back to skill

Security audit

Pomelli AI Brand Marketing Companion

Security checks for vulnerabilities and agentic risk

Overview

This is a document-only marketing helper with broad but purpose-related triggers and no executable or persistent behavior.

Before installing, users should know this skill may activate for general brand-marketing or AI-media requests, not only explicit Pomelli requests. It is otherwise a disclosed, document-only prompt and planning aid with no code execution or credential requirements.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The trigger list includes broad phrases such as "brand marketing," "ai marketing," "brand book," and generic AI media terms that are likely to appear in ordinary user requests unrelated to this specific skill. This can cause unintended skill invocation, routing user context into the wrong capability, and increasing prompt-scope confusion or accidental disclosure of user content to an irrelevant skill.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest sets "language" to "en" and does not mention any user opt-in, language selection, or justification for restricting the skill to English. Under the stated policy, fixed language constraints can be a natural-language policy issue unless they are optional or clearly documented as necessary.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.