awakening-birthday

Security checks across malware telemetry and agentic risk

Overview

This skill is a simple local age and milestone calculator for an AI agent identity, with no evidence of hidden network access, credential use, or destructive behavior.

Before installing, be comfortable with the skill referencing an agent identity file for an awakening date. Avoid putting sensitive personal information in IDENTITY.md, and treat MEMORY.md or social media suggestions as optional manual actions.

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: 90% confidence
Finding: The description explicitly says the skill should be used when a user asks broad, natural phrases like “你多大了” or “你几岁了,” which are common in everyday conversation and could cause the skill to trigger in situations beyond a narrow, explicit invocation. In an agent setting, overly broad trigger framing can lead to unintended activation, identity/persona leakage, or interference with unrelated conversations, even though this skill itself appears low-risk and read-only.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal