Security audit

Seedream 5.0 Lite 直播带货图片

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed AI Hive image-generation helper for livestream commerce assets, with manageable setup and credential-handling cautions but no evidence of deceptive or destructive behavior.

Install in a virtual environment, prefer the config file or environment variable over passing the API key on the command line, only upload images you are allowed to send to AI Hive, and verify generated livestream pricing or promotion fields before publishing.

A.I.G

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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:72
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: scripts/imagegen.py:440
Finding: API Key Exposure Through Command-Line Arguments
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration

Findings (7)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 88% confidence
Finding: The skill invokes shell commands, reads local files, writes results, uses environment variables, and makes network requests, but it does not declare any explicit tool scope or permissions boundaries. That increases the chance an agent platform grants broader-than-necessary capabilities, making prompt-triggered misuse, unintended file access, or unauthorized outbound requests more likely if the skill is invoked in a permissive runtime.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The description contains many broad usage phrases and platform contexts, which can cause over-invocation in unrelated user requests and unnecessarily expose the skill's code-execution and network-capable workflow. In this skill's context, accidental triggering is more concerning because the implementation includes shell and network operations rather than being a purely declarative template.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The module docstring and all user-facing guidance in this file are written exclusively in Chinese, and the CLI prompts/messages throughout the skill assume Chinese as the required interaction language. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 77% confidence
Finding: The top-level description is written in a mixed Chinese/English form, while the remainder of the document is primarily Chinese, with no indication that the skill adapts to the user's preferred language. This can violate a language/locale policy if the organization expects user-facing skills to respect user language choice or obtain opt-in before constraining language.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The example API key value includes the Chinese phrase '请替换为你的APIKey', which imposes a specific language in user-facing configuration text. There is no indication that the skill is region-specific or that users may choose another language, so this appears to violate the language/locale policy criteria.
Content: No source excerpt is available for this finding.

Intent-Code Divergence

Low

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The module docstring says the tool 'only exposes' fixed-model image generation, limited reference-image upload, task query, and API key initialization. In practice, the code exposes those additional capabilities directly as CLI subcommands, including standalone init, task, and upload, which is broader than the narrow 'generation-only' framing suggested by the surrounding skill context and fixed-model wording.
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 skill for producing livestream-related images with Seedream 5 Lite, which naturally covers generation. However, the CLI also exposes separate task and upload commands that let a user query arbitrary generation tasks and upload reference images independently of a generation request, expanding the operational surface beyond the described end-user purpose.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.