Security audit

AI KEY·短剧编剧

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese short-drama writing skill with disclosed draft, memory, compliance-check, and optional video-generation handoff behavior that fits its purpose.

Install this if you want an AI KEY-style Chinese short-drama workflow. Be aware that it expects the broader AI KEY config and reference files, may read and write configured memory/draft locations, and can hand off paid video generation only after confirmation.

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

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (5)

Vague Triggers

Medium

Confidence: 94% confidence
Finding: The trigger list contains broad natural-language phrases such as "write a short drama" and similar generic requests, which can cause the skill to activate when a user did not explicitly intend to invoke this specific tool. That creates unintended routing risk: user content may be steered into this skill's workflow, including file reads, memory access, and downstream tool suggestions, instead of the most appropriate or least-privileged path.

Natural-Language Policy Violations

Medium

Confidence: 87% confidence
Finding: The instruction says action descriptions must be written in Chinese while camera terms remain in English, which imposes a fixed language format. The file later also requires dialogue to be written as '语言：中文普通话', with no opt-in or alternative locale path, creating a language-policy concern.

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: The line specifies dialogue language as '中文普通话' as part of the required format, with no indication that other languages are supported when the user prefers them. This is a natural-language policy issue because it forces a specific locale without opt-in.

Natural-Language Policy Violations

Low

Confidence: 75% confidence
Finding: The audience selection line includes a fixed locale option “海外平台（英文）”, which suggests English output for overseas use. The file does not explicitly state that language choice is user-selectable beyond this preset or justify the locale restriction as a region-specific requirement.

Natural-Language Policy Violations

Low

Confidence: 90% confidence
Finding: The instruction requires Chinese-script screenplay output to use Chinese punctuation and specific quotation marks, which imposes a language/locale constraint in natural language. The file does not indicate that this is optional, user-selected, or limited to a clearly justified region-specific use case.

Static analysis

No suspicious patterns detected.