Security audit

ym-script-to-shotlist

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese skill for turning scripts into shot lists, with no code execution, network use, persistence, or hidden data access.

Install this if you want Chinese-language shot-list drafting from a provided script. Be aware that broad trigger phrases may make it activate for some general filming questions, and users who want English or another language may need to explicitly request that output language.

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
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 (4)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The description advertises broad natural-language triggers around filming and shot listing without strong scope boundaries, which can cause the skill to activate on generic requests like '怎么拍' that may not actually ask for storyboard generation. Over-broad activation can hijack routing from more appropriate skills, leading to incorrect handling of user intent and expanding the skill’s influence beyond its declared purpose.

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The manifest trigger list includes ambiguous terms such as '怎么拍' and 'shot list' without contextual qualifiers, making accidental or overly frequent invocation likely. In an agent ecosystem, this can create prompt-routing collisions, cause unintended disclosure of user context to the wrong skill, or prevent a more specialized skill from handling the request.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: This markdown file is entirely written in Chinese and presents the skill content in a single fixed language. Under the policy rule, forcing a specific language without user opt-in can be a natural-language policy violation when no choice or justification is provided.

Natural-Language Policy Violations

Medium

Confidence: 94% confidence
Finding: The entire template and its required field labels are specified in Chinese, and there is no natural-language indication that users may choose another language or locale. This creates a language policy concern because the skill appears to impose a specific language by default rather than offering a choice.

Static analysis

No suspicious patterns detected.