Back to skill

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 AI image-generation helper that uploads user-selected reference images to AI Hive and saves generated results locally.

Install only if you trust AI Hive with the reference images and prompts you provide. Use a virtual environment, consider setting the API key via environment variable or reviewing ~/.ai-hive/config.json permissions, and be aware that generated files are saved under ~/Downloads/AiHive by default.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/imagegen.py:219
Finding

Unvalidated API-Controlled Upload and Download Destinations

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Note
Location
SKILL.md:76
Finding

Unpinned Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (7)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill invokes shell commands, installs Python packages, reads local files, writes outputs, and makes network requests, yet it declares no explicit tool or permission boundaries. This creates an avoidable trust gap: an agent may grant broader-than-necessary capabilities or execute the skill without clear user-visible scoping, increasing the risk of unintended file access, command execution, or outbound requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest description says to use the skill for a long list of phrases such as '品牌 IP', '吉祥物', '虚拟人', '绘本角色', and '商业角色图片', which are broad topic labels rather than specific invocation conditions. Without explicit scope constraints or negative examples, this could cause the skill to match ordinary image-generation requests beyond the intended character-consistency workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The file's instructions and examples are written as mandatory Chinese-language operating guidance, and there is no statement allowing the user to choose another language or explaining that the skill is intentionally limited to a Chinese locale. This can violate language/locale policy when the skill is used in broader contexts without user opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

该文件的模块说明、错误提示和 CLI 交互文案均为中文,且未见任何语言切换、用户选择或区域限定说明。根据规则,强制特定语言而没有用户 opt-in 属于自然语言层面的组织策略违规。

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The example placeholder value uses Chinese text ('请替换为你的APIKey') in a way that assumes a specific language for users reading or copying the config. Because this file does not offer a language choice or document a locale-specific scope, it can violate the policy against forcing a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

Although the skill fixes the model ID, it accepts unrestricted key=value pairs and forwards them directly as params to the image generation API. For a narrowly described character-consistency skill, exposing arbitrary backend parameters enables capabilities and behaviors beyond the documented, constrained workflow.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest describes a character-consistency image generation skill using a fixed Seedream 5 Lite model, but this file additionally provides task and upload subcommands that operate independently of generation. Those capabilities are broader utility operations not reflected in the manifest's user-facing purpose of building consistency bibles and shot-change outputs.

Content

No source excerpt is available for this finding.