Security audit

公众号爆款封面生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent WeChat cover-image generation skill, with ordinary third-party API, credential, upload, download, and dependency hygiene risks users should understand.

Install only if you are comfortable using AI Hive for this workflow. Use a virtual environment, avoid passing the API key on the command line, upload only images you are authorized to share, and treat downloaded results as untrusted files until opened or processed safely.

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 (3)

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

Warning

Location: scripts/imagegen.py:231
Finding: Unvalidated API-Supplied Upload and Download Destinations
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Note

Location: scripts/imagegen.py:441
Finding: API Key Accepted Through Process Command-Line Arguments
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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 (5)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 92% confidence
Finding: The skill invokes shell commands, accesses local files, uses environment-dependent execution, and makes network requests, but it does not declare any tool restrictions or permission boundaries. This creates unnecessary ambient authority: an agent/runtime may permit broader capabilities than the skill actually needs, increasing the chance of unintended file access, command execution, or exfiltration through the fixed API workflow.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file’s user-facing description and operational guidance are written entirely in Chinese and repeatedly target WeChat public-account workflows, but it does not explicitly state that the skill is China/Chinese-only or offer an opt-in language choice. Under the policy, forcing a specific language or locale without user choice is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The file-level docstring and all user-facing CLI messages are written only in Chinese, which imposes a language choice on users without any opt-in or alternative locale support. This matches the policy category for language/locale constraints expressed in natural-language content.
Content: No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The manifest scope is specifically about generating WeChat official account covers, share cards, and related series visuals. However, the in-code SKILL_CONFIG search text explicitly targets broader commercial use cases such as e-commerce main images, product detail pages, ads, posters, and social media image sets, which exceeds the manifest's narrower stated purpose.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Low

Category: Not specified by scanner
Confidence: 79% confidence
Finding: The manifest describes a skill for generating and editing WeChat article cover images via AI Hive. In addition to generation-related operations, the code opens the user's web browser to an account/chat page and guides interactive API key creation, which is not part of the image-generation task itself and introduces an extra capability beyond the stated creative purpose.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.