ClawHub
Back to skill

Security audit

video-marketing

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward video marketing guidance skill with no hidden execution, persistence, or sensitive authority.

Installers should expect this skill to help draft and plan video marketing content. It can use existing project context files to tailor recommendations, so users should keep those files free of information they would not want reflected in marketing outputs.

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
91% confidence
Finding

The manifest says to use the skill whenever the user wants to 'plan video marketing' or 'create video scripts,' which are broad intents rather than tightly scoped trigger phrases. Although some examples are specific, the activation guidance does not include clear exclusions or negative examples, so the skill could be invoked for general marketing or writing requests that are not meant for this skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.