ClawHub
Back to skill

Security audit

tiktok-shop-video

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently provides video scripts, filming guidance, and optional paid AI clips, with no evidence of hidden or unrelated behavior.

Optional AI clips send product photos and prompts through Varg to generation services and consume credits. Use materials you are authorized to share and review the estimate before approving. Confirm current TikTok rules for your market before posting.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The AI b-roll workflow does not warn that product photos and prompts are sent to external generation services.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow instructs the agent to use the real product photo as a reference for externally hosted image and video generation. Although it requires approval of the credit estimate, it does not disclose the transfer of user-provided images and prompts to third-party services; cost approval is not a privacy warning.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.