Security audit

电商爆款主图生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for AI image generation, but it needs review because remote API response fields can influence local downloads and file paths.

Review this skill before installing. Only use it with an AI Hive account and images you intend to upload, prefer an isolated Python environment, and avoid running it in sensitive networks or directories until result URL validation and safe filename containment are added.

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)

T09 · Insecure Skill Coding Practices

Error

Location: scripts/imagegen.py:349
Finding: Server-Controlled Filename Components Permit Path Traversal and File Overwrite
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/imagegen.py:264
Finding: Unvalidated Remote Result URLs Enable Client-Side Requests to Internal Resources
Content: View full analysis
Remediation: View remediation

T08 · Insecure Dependencies

Note

Location: SKILL.md:76
Finding: Runtime Dependency Is Installed Without Version or Integrity Pinning
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
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 (4)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 88% confidence
Finding: The skill exposes shell, network, file read/write, and environment-backed behavior through documented script invocations, but it does not declare any explicit tool scope or permissions boundaries. That makes the operational surface larger and less reviewable, increasing the chance that an agent invokes filesystem or network actions unexpectedly, especially because the script can query a remote API and save generated outputs locally.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The description is very broad and covers many common e-commerce image tasks across multiple platforms, which can cause the skill to trigger for routine user requests beyond the author's intended context. Over-broad invocation raises the risk of accidental tool use, unnecessary file/network access, or the skill steering unrelated requests into scripted execution when a simpler non-tool response would have been safer.
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 instructions are written only in Chinese, and the script's prompts, help text, and status messages consistently assume Chinese-language operation. Because the file contains no opt-in, fallback, or justification that this is a region-specific skill, this is a natural-language locale policy violation under the stated rule.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 71% confidence
Finding: The title and operating instructions are primarily in Chinese, and the description is written as though the skill is intended to run in Chinese by default, while also embedding English platform names. There is no statement offering the user a language choice or clarifying that output language follows user preference, which can violate language/locale policy expectations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.