Back to skill

Security audit

AI电商专家|电商文生视频

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent IMIVA video-generation integration, but it runs an unpinned npm package at runtime with the user's token and full inherited environment.

Review before installing. Use it only with a dedicated IMIVA token, avoid running it from environments containing unrelated secrets, and prefer a pinned or locally vetted MCP package version over `@latest`. Confirm costs before creating non-dry-run video tasks and keep the token out of chats, screenshots, and repositories.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (1)

T08 · Insecure Dependencies

Warning
Location
scripts/imiva_mcp.py:13
Finding

Unpinned npm Package Is Retrieved and Executed at Runtime

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (8)

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
96% confidence
Finding

Using os.environ.copy() passes the entire parent environment to the spawned npm package, potentially exposing unrelated secrets such as cloud credentials, CI tokens, proxy credentials, and internal configuration. In this skill's context, the child process is an external package fetched via npx, so broad environment inheritance materially increases the blast radius of any malicious or compromised dependency.

Content

Scanner excerpt · scripts/imiva_mcp.py (reported line 51)May include surrounding context.

python
def invoke(method: str, params: dict | None = None) -> dict:
    npx, token = require_runtime()
    env = os.environ.copy()
    env["MCP_TOKEN"] = token
    env["API_URL"] = os.environ.get("IMIVA_API_URL", os.environ.get("API_URL", DEFAULT_API_URL))
    proc = subprocess.Popen(

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill includes operational instructions that rely on shell execution, environment variables, and local file access, but it does not declare any explicit tool scope such as allowed-tools or permissions. This can cause an agent platform to over-grant capabilities or invoke the skill in contexts where users and orchestrators are not clearly informed about the required access, increasing the risk of unintended command execution or exposure of local paths and secrets.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description uses broad activation language like 'Use this skill for IMIVA ecommerce content' across many adjacent workflows without clear trigger boundaries. In agentic environments, this can make the skill eligible for invocation in loosely related contexts, increasing the chance that external tools are called or paid video-generation tasks are proposed when the user did not explicitly request this specific integration.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The metadata fixes the language to zh-CN, and the document later states it is especially suitable for Chinese users, but does not indicate this is an opt-in or region-justified constraint. This can violate language/locale policy when a skill forces a specific language experience without giving the user a choice.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The phrase saying the skill is particularly suitable for Chinese users implies a locale-specific preference in natural-language instructions. Because the file does not clearly present this as optional or justified by a strict regional requirement, it may conflict with policy against forcing a language or locale without user choice.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The script forwards the MCP_TOKEN credential to an externally fetched npm package without any explicit user disclosure, confirmation, or minimization of what is shared. Because the package is referenced as @latest and executed through npx, users may unknowingly expose sensitive credentials to updated third-party code, increasing supply-chain and secret-handling risk.

Content

No source excerpt is available for this finding.

subprocess module call

Medium
Category
Dangerous Code Execution
Confidence
70% confidence
Finding

subprocess module calls execute external commands. Without careful input validation, this enables command injection.

Content

Scanner excerpt · scripts/imiva_mcp.py (reported line 54)May include surrounding context.

python
env = os.environ.copy()
    env["MCP_TOKEN"] = token
    env["API_URL"] = os.environ.get("IMIVA_API_URL", os.environ.get("API_URL", DEFAULT_API_URL))
    proc = subprocess.Popen(
        [npx, "-y", PACKAGE],
        stdin=subprocess.PIPE,
        stdout=subprocess.PIPE,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

All user-facing error strings shown here are hard-coded in Chinese, while the file provides no opt-in, locale detection, or alternative language selection. This creates a natural-language policy issue when a skill imposes a specific language on users without documented justification.

Content

No source excerpt is available for this finding.