Time Anchor

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed local date-calculation helper with a broad trigger, but it does not show hidden access, credential use, persistence, or destructive behavior.

Install this if you want your agent to run a local Python helper for date-related questions. Be aware it may activate on broad scheduling or 'when' phrasing, and avoid storing sensitive private event names in the editable TARGETS list or asking it to web-search confidential events.

SkillSpector

By NVIDIA

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (1)

Vague Triggers

Medium

Confidence: 96% confidence
Finding: The manifest says the skill triggers on any message mentioning dates, deadlines, timeframes, "when," planning, scheduling, or temporal reasoning. Several of these terms are common in everyday conversation and the file does not provide narrowing constraints or negative examples, making invocation scope ambiguous.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal