Back to skill

Security audit

Utf8 Time

Security checks for vulnerabilities and agentic risk

Overview

This skill only prints the current time, with low-impact routing and formatting issues but no evidence of hidden access, persistence, exfiltration, or destructive behavior.

This appears safe to install for showing the current time. Users should be aware it may trigger on the word "now" in unrelated prompts, and its output uses Chinese locale date formatting rather than adapting to the user's locale.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
98% confidence
Finding

The trigger phrase "now" is extremely broad and commonly appears in ordinary conversation, which can cause the skill to activate unintentionally in many unrelated contexts. This creates an over-permissive invocation surface, increasing the chance of unexpected execution and response hijacking when users are not actually asking for the time.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The description says the skill activates when the user mentions the current time, but it does not define clear scope boundaries or disambiguation rules. Ambiguous activation criteria can lead to accidental triggering in benign discussion about time, reducing user control and making routing behavior less predictable.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The call to toLocaleString hard-codes the locale to 'zh-CN', which imposes a specific language/locale behavior on all users. This matches the policy category for language or locale constraints because the file provides no opt-in, fallback, or justification for restricting output to Chinese formatting.

Content

No source excerpt is available for this finding.