Back to skill

Security audit

EMAR adv-video-script-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese advertising video script-writing skill with no executable code, persistence, or hidden data access.

Safe to install for generating Chinese ad video scripts. Review generated advertising claims such as prices, stock limits, sales volume, or guarantees before use so they match the actual product offer and legal requirements.

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
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The manifest description and main instructions are written as a Chinese-only assistant specification, describing the skill as producing scripts in Chinese and positioning the assistant in that language context. There is no indication that the user can choose another language or locale, which can violate language/locale policy when imposed by default.

Content

No source excerpt is available for this finding.