Security audit

Vlog

Security checks for vulnerabilities and agentic risk

Overview

This markdown-only skill is not malicious, but it claims travel booking and boarding-pass functions that do not match its Travel Vlog editing description.

Review this skill carefully before installing. It should be treated as a travel-service assistant rather than a vlog-editing helper, and users should not rely on it for tickets, check-in, itineraries, or boarding passes unless the publisher clearly documents the data sources, permissions, account access, and user confirmation steps.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Description-Behavior Mismatch

High

Confidence: 98% confidence
Finding: The skill metadata advertises a travel-video editing and shooting assistant, but the body describes travel booking, flight status, weather, itinerary, and boarding-pass capabilities. This scope mismatch can cause the agent to invoke the skill in unrelated contexts and mislead users about data access or operational authority, increasing the chance of unintended routing, overbroad activation, and unsafe handling of travel-related requests.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: Natural-language policy requires avoiding forced language or locale constraints unless users can opt in or the restriction is clearly justified. This file presents the skill entirely in Chinese and does not state that it is China-specific or offer multilingual use.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The example trigger phrases are generic enough to match broad help-style user requests rather than a narrowly scoped invocation for this specific skill. In an agent environment, overly broad prompts can cause accidental selection of the skill for unrelated tasks, especially dangerous here because the documented capabilities already exceed the declared purpose.

Static analysis

No suspicious patterns detected.