Back to skill

Security audit

World Timezone Pro

Security checks for vulnerabilities and agentic risk

Overview

This is a simple timezone utility with quality problems, but I found no hidden data access, persistence, network behavior, destructive actions, or credential handling.

Install only if you are comfortable with a rough local timezone script. Do not rely on its conversion output for meetings, travel, deadlines, or business decisions until the conversion logic and documentation are fixed.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • 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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (9)

Tp4

High
Category
MCP Tool Poisoning
Confidence
93% confidence
Finding

The skill's documented behavior substantially diverges from its actual implementation, including unsupported features and undisclosed business-hours/meeting-status logic. Description-behavior mismatch is dangerous because it undermines informed consent and security review, and hidden or undocumented behaviors can mask data handling or execution paths users did not agree to.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The skill metadata and command interface promise timezone conversion, but the implementation does not perform conversion of the requested input time at all. This is dangerous because it creates a trust gap: users rely on the feature for real-world coordination, yet the result is misleading and can produce operational errors.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The convert command accepts a user-supplied time and claims to convert it between cities, but it ignores that value and instead reports the cities' current times. In a scheduling or business context, this can mislead users into making incorrect meeting, travel, or deadline decisions because the output appears authoritative while being functionally wrong.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill advertises executable shell-backed capability but does not declare any tool scope such as permissions or allowed-tools. This creates an authorization and review gap: an agent or platform may permit broader execution than users expect, making it harder to constrain or audit command execution safely.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README mixes English metadata with Chinese user-facing instructions and feature descriptions, but the main instructional content from L09 onward is Chinese-only. This can impose a language preference on users without opt-in, which matches the policy category for language or locale violations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This code file contains natural-language strings such as the title and later user-facing status messages in Chinese, but it does not provide any opt-in or alternative locale. Under the policy for natural-language violations, forcing a specific language without user choice is in scope for all file types.

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/timezone.py (reported line 137)May include surrounding context.

python
def get_time_in_tz(tz_name: str) -> dict:
    """Get current time in a given timezone."""
    try:
        result = subprocess.run(
            ["date", "-u", "+%Y-%m-%d %H:%M:%S %z %Z"],
            env={"TZ": tz_name},
            capture_output=True, text=True, timeout=5

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest describes a timezone conversion and lookup utility, which does not inherently require spawning OS processes. The implementation uses subprocess.run to execute the system date command, introducing command-execution capability beyond what is normally expected for a simple world-clock skill.

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/timezone.py (reported line 222)May include surrounding context.

python
print(json.dumps({"error": "City not found in timezone map"}))
        return
    try:
        result = subprocess.run(
            ["date", "-j", "-f", "%H:%M", time_str, "+%H:%M %Z"],
            env={"TZ": from_tz},
            capture_output=True, text=True, timeout=5