Security audit

WBFlow·第4环提示词

Security checks for vulnerabilities and agentic risk

Overview

This skill turns local story and storyboard files into image and video prompts, with clearly scoped behavior and no material security concerns found.

Expect this skill to write 04_prompts/prompts.json and generate image prompts mainly in English. It requires the WBFlow companion skills; review those separately before installing the full pipeline.

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 image prompt specification requires predominantly English output without user opt-in.

Low

Category: Output Handling
Confidence: 98% confidence
Finding: The image_prompt specification explicitly requires prompts to be primarily in English (英文为主). The skill provides neither a user language choice nor a documented technical justification for this language constraint.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.