ClawHub

Sora 478958

Security checks across malware telemetry and agentic risk

Overview

This appears to be a Sora help/tutorial skill with overly broad activation wording, but no evidence of hidden, persistent, destructive, or high-impact behavior.

Before installing, consider whether you want a broad Sora help skill that may activate during general Sora conversations. The available scan evidence is clean, but broad triggers can be inconvenient if you prefer explicit skill invocation.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger includes very broad phrases such as "Sora" and related tutorial keywords, which can cause the skill to activate during ordinary discussion rather than a clear request to use this specific skill. This creates prompt/skill hijacking risk and unintended behavior because unrelated user conversations about Sora could invoke the skill without sufficient intent verification.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The activation condition "用户需要Sora相关帮助" is highly ambiguous and effectively matches any Sora-related assistance request. In a shared assistant environment, this can overreach into many benign Sora conversations, causing accidental activation and reducing user control over which skill is applied.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal