Security audit

Live Engagement

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only TikTok Shop livestream planning skill with mild privacy guidance gaps, but no executable or hidden behavior.

Installers should understand this is guidance for live selling operations, not code. When using it, collect only the metrics needed, avoid storing personal audience data unnecessarily, contact giveaway winners through official platform workflows, and follow TikTok policies plus applicable privacy and consumer-promotion rules.

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 (3)

Missing User Warnings

Medium

Confidence: 83% confidence
Finding: This markdown skill directs users to collect and review engagement metrics, follower growth, comment sentiment, and viewer drop-off data. Because SQP-2 applies to markdown files when behaviours could affect privacy, the description should explicitly warn that analytics and comment data may involve user information and should be handled in accordance with platform policies and privacy obligations.

Missing User Warnings

Low

Confidence: 86% confidence
Finding: The playbook instructs moderators to contact giveaway winners via comment or DM immediately, but provides no guidance on minimizing collection of personal data, verifying official contact channels, or avoiding solicitation of sensitive information. In a livestream commerce context, this can lead to unsafe handling of user information, impersonation/scam risk, and inconsistent privacy practices by operators.

Missing User Warnings

Low

Confidence: 83% confidence
Finding: This markdown file asks operators to record post-show performance data such as comments, shares, followers, and viewer metrics, but it provides no warning or guidance about handling user-related platform data. Under the markdown-file criteria for missing user warnings, this is a mild privacy-affecting behavior that should be disclosed or bounded.

Static analysis

No suspicious patterns detected.