Back to skill

Security audit

AI电商专家|天猫 图片视频全内容

Security checks for vulnerabilities and agentic risk

Overview

The skill mostly matches its ecommerce-content purpose, but it runs a mutable external npm MCP package with broad environment-variable access and permissive invocation behavior that users should review before installing.

Install only if you trust the IMIVA npm MCP package and are comfortable with it receiving your MCP token and any environment variables present when the helper runs. Prefer a pinned package version, a minimal environment, explicit user confirmation before paid generation, and manual invocation for specific Tmall tasks rather than broad implicit use.

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 (2)

T08 · Insecure Dependencies

Error
Location
scripts/imiva_mcp.py:14
Finding

Mutable npm Dependency Is Downloaded and Executed Automatically

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
scripts/imiva_mcp.py:51
Finding

Third-Party MCP Process Inherits the Complete Parent Environment

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
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (10)

Tp4

High
Category
MCP Tool Poisoning
Confidence
96% confidence
Finding

The skill is advertised as a narrow Tmall ecommerce content workflow, but its documented behavior includes generic tool discovery and the ability to invoke broadly available MCP functionality without enforcement of task-specific limits. This mismatch is dangerous because users and higher-level agents may trust the description while the actual capability surface is much wider, enabling unintended actions, data access, or misuse of privileged tools.

Content

No source excerpt is available for this finding.

Env Variable Harvesting

High
Category
Data Exfiltration
Confidence
95% confidence
Finding

The code copies the entire parent environment with os.environ.copy() and passes it to a network-fetched external CLI. That needlessly exposes all ambient secrets and configuration in the current process environment—not just MCP_TOKEN—to the child package, which is especially risky here because the package is invoked through npx and may change over time.

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
93% confidence
Finding

The skill exposes shell, file read, and environment-variable access but does not declare any explicit tool scope or allowed-tools boundary. In practice, this creates an over-privileged skill surface where natural-language requests or embedded workflow steps could cause access to secrets, local files, or arbitrary command execution beyond the stated ecommerce purpose.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description ends with 'Use this skill for IMIVA ecommerce content, product images, product detail pages, KOC seeding, product video, viral creative recreation, marketplace listing and social commerce workflows.' This reads like a broad activation description rather than a narrowly scoped trigger, and several phrases such as 'product images' or 'marketplace listing' are common requests that could match many unrelated conversations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The description states the skill is especially suitable for '中文用户', and the example task arguments hard-code 'language':'简体中文' rather than presenting language as a user choice. Under the policy, locale constraints should be optional or clearly justified as region-specific; here the file targets Tmall but does not explicitly state that output language is mandatory or user-selectable.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill enables allow_implicit_invocation without any visible trigger restrictions, scope limits, or exclusion conditions. That means the agent may auto-select this commerce-content skill in broader conversations than intended, potentially sending user prompts or business assets into content-generation workflows without clear user intent or confirmation.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

This code reads the MCP_TOKEN environment variable and later injects it into the child process environment for the spawned MCP client. Although the script validates presence of the token, it does not provide a user-facing warning, log message, or comment disclosing that a credential will be consumed and forwarded to an external package process.

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
91% confidence
Finding

The script executes an external package via npx using @infimind/ecom-content-cli@latest, which can fetch and run code that is not pinned to a known version. In an enterprise ecommerce skill that handles authenticated content-generation workflows, this creates a significant supply-chain risk: a compromised or malicious package update would run with access to the user's environment, including MCP credentials.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script's user-facing error messages are written only in Chinese, and there is no indication that the skill is intentionally region-specific or that users can opt into another language. This can violate language/locale policy when a skill implicitly forces a language without documented justification.

Content

No source excerpt is available for this finding.