Back to skill

Security audit

Amazon 亚马逊 电商视频生成与编辑

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly aligned with Amazon product video generation, but review is warranted because its API token can be sent to a configurable server and generated downloads can overwrite files if task metadata is malicious.

Install only if you trust AI Hive and the environment where this runs. Use a dedicated low-privilege API key, do not set custom base URLs unless you control them, run it in an isolated virtual environment, and avoid processing task IDs or API responses from untrusted servers until filename and origin validation are fixed.

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/videogen.py:89
Finding

API Credential Disclosure Through an Unrestricted Base URL

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/videogen.py:399
Finding

Path Traversal and Arbitrary File Overwrite in Generated-Media Downloads

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
SKILL.md:79
Finding

Unpinned Third-Party Dependency Installation

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · SKILL.md (reported line 37)May include surrounding context.

md
--prompt 'Amazon product setup video based only on the merchant-approved instructions: lay out the supplied parts, show step 1, step 2 and step 3 in order with clear hand placement, then show the correctly assembled result. Do not skip safety steps, invent a component or display unprovided measurements.'

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill invokes local scripts and documents capabilities that imply shell, file, environment, and network access, but it does not declare any explicit tool scope or permission boundaries. This increases the risk of overbroad execution in an agent environment, making it easier for a caller or downstream prompt to use the skill with more privileges than intended.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The file advertises and exposes a broad, general-purpose AI Hive client with text chat, image generation, model enumeration, media upload, and task polling, while the declared skill scope is Amazon ecommerce video generation/editing. This scope drift increases attack surface and permits capability abuse outside the reviewed intent, which can lead to unauthorized or unexpected use of the skill in agent environments that rely on manifest-level least privilege assumptions.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Text chat and image-generation features materially exceed the stated purpose of an Amazon product video editing/generation skill. In agent ecosystems, these hidden extra capabilities can bypass user and platform expectations, enabling prompt misuse, unreviewed content generation paths, and broader data exfiltration or policy evasion opportunities than the skill description suggests.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file contains user-facing natural language exclusively in Chinese across the substantive changelog entries. Under the policy rule for language/locale, this can be a violation when a skill forces a specific language without user opt-in or justification.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The description contains both English and Chinese terms, which indicates language-specific behavior or targeting. The file does not explicitly state that users can choose their preferred language or that this multilingual scope is limited to a justified locale-specific context.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

The example API key placeholder uses Chinese text ('请替换为你的APIKey'), which imposes a specific language in user-facing configuration content. 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.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This code file includes natural-language descriptions and instructions exclusively in Chinese in the module docstring. Under the policy, language constraints should not be forced without opt-in or a clearly documented justification, and no alternative language option is offered here.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The user-info endpoint exposes account metadata and wallet/balance information that is unrelated to Amazon video creation. In a skill context, this is an unnecessary sensitive-data access path that could be used for reconnaissance or privacy leakage if an agent or caller invokes it unexpectedly.

Content

No source excerpt is available for this finding.