Security audit

Seedream 5.0 Lite 角色一致性图片

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed image-generation helper that uploads user-specified reference images to a fixed AI Hive API and saves generated outputs locally.

Install only if you are comfortable sending the selected reference images and prompts to AI Hive. Use authorized character or person references, review generated outputs for rights and endorsement issues, and protect the AI Hive API key stored in the environment or local config file.

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (2)

Lp3

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill exposes shell, file, environment, and network capabilities through documented command invocations, yet it declares no permissions or capability boundaries. This creates a transparency and policy-enforcement gap: a user or platform may invoke the skill without understanding it can read local files, write outputs, access environment-backed credentials, and make outbound requests.

Vague Triggers

Medium

Confidence: 73% confidence
Finding: The description includes many broad trigger phrases spanning character consistency, brand IP, mascots, comics, storyboards, memes, social media, and commercial character images. Overbroad activation can cause the skill to be selected for loosely related requests, increasing the chance that code-capable behavior runs in contexts where users did not intend file upload, local script execution, or external API use.

Static analysis

No suspicious patterns detected.