Back to skill

Security audit

AI电商专家|3C 数码电商图片视频

Security checks for vulnerabilities and agentic risk

Overview

The skill matches an IMIVA ecommerce content workflow, but it runs an unpinned npm package with an MCP token and the full local environment, which needs review before installation.

Review before installing. Use only a narrowly scoped IMIVA token, avoid running it from a shell that contains unrelated secrets, and prefer a pinned npm package version or controlled MCP configuration before using billable generation workflows.

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

Error
Location
scripts/imiva_mcp.py:14
Finding

Automatic Execution of an Unpinned npm Package with Inherited Credentials

Content
View full analysis
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( [npx, "-y", PACKAGE], stdin=subprocess.PIPE, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, bufsize=1, env=env, ) ``` `references/mcp-config.example.json:4-9`: ```json "command": "npx", "args": [ "-y", "@infimind/ecom-content-cli@latest" ], "env": { ``` `SKILL.md:87-93`: ```json "command": "npx", "args": [ "-y", "@infimind/ecom-content-cli@latest" ], "env": { "MCP_TOKEN": "your-token-here", ``` ### Technical Analysis The executable dependency is identified using the mutable npm tag `@latest` rather than an audited, exact version. The `npx -y` invocation automatically obtains and executes whichever release the package registry resolves as the latest version at runtime, without an interactive installation confirmation. Consequently, reviewing the repository does not establish the identity or integrity of the code that will execute during a future Skill invocation. A later package release can change the effective executable payload without any modification to this repository. The exposure is amplified by the child-process environment. The helper copies the complete parent environment with `os.environ.copy()`, explicitly adds `MCP_TOKEN`, and supplies that environment to the remotely obtaine ...[truncated 2017 chars]
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Behavioral ASTexec() Call, eval() Call, Dynamic Import
  • 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
Findings (7)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The skill is presented as a narrowly scoped 3C ecommerce image/video workflow, but its documented behavior includes listing all token-available MCP tools and generically invoking tools by name. That creates a privilege-expansion risk: once a powerful IMIVA token is present, the skill can reach beyond the advertised workflow into any MCP capability exposed to that token, violating user expectations and increasing blast radius.

Content

No source excerpt is available for this finding.

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
89% confidence
Finding

The code copies the entire parent environment with os.environ.copy() and passes it to an externally fetched npx package. In this skill context, that is more dangerous because the helper is explicitly designed to run third-party MCP tooling, so any unrelated secrets present in the environment could be exposed to the child process or its dependencies unnecessarily.

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
87% confidence
Finding

The skill documents shell execution, environment-variable use, and file-path handling, but does not declare any explicit tool scope such as allowed tools or permissions. That weakens least-privilege controls and can let the hosting agent expose broader local capabilities than users would reasonably expect from an ecommerce content skill, especially when local file paths and tokens are involved.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The markdown states the skill is especially suitable for Chinese users, which creates a locale-specific targeting constraint. Elsewhere, example invocations also hard-code language":"简体中文", but the document does not offer users a language/locale choice or explain a justified compliance need for restricting language.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script presents user-facing runtime errors only in Chinese, such as the missing npx and missing MCP_TOKEN messages. This imposes a specific language on users without opt-in or documented locale scope, which matches the language/locale policy violation criteria.

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,

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
81% confidence
Finding

The script requires and accesses the MCP_TOKEN environment variable, which is a sensitive credential, but provides no prior user-facing warning beyond an error message if it is missing. In this file there is no comment, docstring, prompt, or explicit disclosure that the token will be consumed and forwarded to a child process.

Content

No source excerpt is available for this finding.