Security audit

gtrk 旅拍解说

Security checks for vulnerabilities and agentic risk

Overview

This skill creates Chinese-narrated travel videos through a purpose-aligned workflow with disclosed cloud processing, charges and approval checkpoints.

Use this skill if you want Chinese narration and accept cloud processing of selected media and text. Check initial analysis costs as well as production estimates, review music licensing, and ensure the required companion skills are available.

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 skill mandates Chinese narration without asking the user to choose or opt into the output language.

Medium

Category: Output Handling
Confidence: 88% confidence
Finding: The mandatory writing rules require Chinese phrasing, and the workflow defines the deliverable as a Chinese-narrated video. However, activation includes language-neutral requests such as “travel recap”; the language question at line 60 concerns source transcription, not the user's preferred output language.
Content: No source excerpt is available for this finding.