Back to skill

Security audit

AI电商专家|跨品类爆款图改造

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its ecommerce image workflow purpose, but it needs Review because it runs an unpinned npm MCP client with inherited environment secrets and exposes a broad MCP tool-call helper.

Review this before installing. Use it only with a narrowly scoped, revocable IMIVA token and avoid running it in an environment that contains unrelated API keys or cloud credentials. Prefer a pinned reviewed version of the npm client and a minimal environment allowlist before operational use, and verify which MCP tools the token can access before allowing the generic call helper.

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:13
Finding

Mutable npm Package Is Automatically Downloaded and Executed with Sensitive Environment Variables

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (10)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill is presented as a dedicated cross-category viral image transformation workflow, but the referenced usage patterns show a generic MCP client that can list tools and invoke arbitrary tool names. That mismatch is dangerous because users and orchestrators may trust the skill with permissions appropriate for one narrow function while it can actually reach additional token-authorized capabilities, expanding the attack surface and enabling privilege misuse.

Content

No source excerpt is available for this finding.

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
94% confidence
Finding

Using os.environ.copy() passes the full parent environment into a child process that executes externally sourced npm code. If the host environment contains additional secrets, cloud credentials, CI tokens, proxy settings, or internal configuration, the child process gains access to all of them, magnifying the impact of any compromised package or unexpected tool behavior.

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
96% confidence
Finding

The skill exposes shell, file-read, and environment-dependent behaviors without declaring any explicit tool scope or allowlist, so a host agent may grant broader capabilities than users expect. In context, the document instructs use of local files, environment tokens, and command execution, which increases the risk of unintended access to sensitive files or secrets if the wrapper script or agent follows those instructions automatically.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The description explicitly says the skill is especially suitable for '中文用户', which imposes a language/locale preference in natural language. The file does not offer an opt-in choice for other languages or explain a necessary compliance or region-specific reason for restricting the skill to Chinese users.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The display name, short description, and default prompt are all written exclusively in Chinese, which indicates a language-specific interaction requirement. The file does not provide any opt-in, alternative locale, or justification that this skill is intentionally region-specific, so it appears to impose a language constraint contrary to the stated policy.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
85% confidence
Finding

The script reads MCP_TOKEN from the environment and then injects it into the child process environment for the npm-based MCP client. While the error message explains that the token must be provided, there is no explicit warning that the credential will be passed to a subprocess or used in external network-backed tooling.

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

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The code runs npx -y @infimind/ecom-content-cli@latest, which fetches and executes a remote npm package at runtime without pinning a version or clearly warning the operator. This introduces supply-chain risk: a compromised upstream package, malicious publish, or unexpected latest-version behavior would execute code in the local environment with access to the provided token and inherited environment.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The wrapper advertises a narrowly scoped ecommerce image-migration skill, but the implementation accepts an arbitrary tool name and forwards arbitrary arguments to tools/call. That creates a capability-expansion issue: any IMIVA MCP tool available to the token can be invoked, which breaks least privilege and could expose unrelated high-impact actions through a misleadingly narrow skill surface.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The script's user-visible error messages are written only in Chinese, and the CLI description/help text also uses Chinese. There is no indication that this tool is intentionally restricted to Chinese-speaking users or any mechanism for opting into another language.

Content

No source excerpt is available for this finding.