Back to skill

Security audit

Query Customer Service Record

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says, but it can query sensitive customer service records through an unauthenticated and caller-configurable API endpoint.

Review this skill before installing. It is not deceptive or destructive, but it should only be used in an environment where the API endpoint is trusted, network egress is controlled, and access to customer service records is authorized outside the skill. Prefer a version that pins or allowlists the API host, requires HTTPS, and uses authenticated requests.

Vulnerability Patterns
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
  • 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)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/query_service.py:30
Finding

Unrestricted API Base URL Enables Server-Side Request Forgery

Content
View full analysis
Remediation
View remediation

T05 · Unauthorized Access and Privilege Escalation

Error
Location
SKILL.md:108
Finding

Customer and Service Records Are Queried Without Authentication or Authorization Context

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill invokes a Python script that performs remote API requests, but the manifest does not declare any explicit tool scope or network permission boundaries. This creates an undeclared capability gap: an agent or reviewer cannot easily tell that customer identifiers and query parameters will be sent off-box, increasing the risk of unexpected data exfiltration or overbroad execution in environments that rely on manifest-level restrictions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill handles customer names and retrieves service records, which are likely business-sensitive and may contain personal or operational details, yet it does not warn users that these identifiers and records are transmitted to a remote API. In this context, the omission is more dangerous because the skill is specifically designed to query customer service history, so users may disclose sensitive customer information without informed consent or awareness of external processing.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

Natural-language strings, docstrings, comments, and CLI usage are consistently presented only in Chinese, which can amount to a language/locale policy violation when no opt-in or justification is provided. The file does not indicate that this is a region-specific tool or offer multilingual support.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
83% confidence
Finding

This function transmits customer-identifying query data to an externally supplied base_url without any validation or allowlisting of the destination. If an attacker can influence base_url, the skill could exfiltrate customer data to an untrusted host or send it over insecure transport, which is more sensitive here because the skill explicitly handles customer service records.

Content

Scanner excerpt · scripts/query_service.py (reported line 35)May include surrounding context.

python
payload = {"customerName": customer_name}
    
    try:
        response = requests.post(url, json=payload, timeout=30)
        response.raise_for_status()
        result = response.json()

External Transmission

Medium
Category
Data Exfiltration
Confidence
85% confidence
Finding

This request sends customer name plus service-record date range to an externally controlled endpoint, and the response may contain sensitive customer service details. If base_url is attacker-controlled or misconfigured, the skill can leak both query parameters and returned business data to an unauthorized system, increasing risk beyond a simple lookup.

Content

Scanner excerpt · scripts/query_service.py (reported line 71)May include surrounding context.

python
}
    
    try:
        response = requests.post(url, json=payload, timeout=30)
        response.raise_for_status()
        result = response.json()

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

This code file sends customer-provided names to a remote service via requests.post, which is a network operation involving potentially sensitive business data. While the function purpose implies querying a service, the script does not provide any explicit runtime disclosure, confirmation, or privacy warning to the user before transmitting that data.

Content

No source excerpt is available for this finding.