ClawHub

Linux Edc9f0

Security checks across malware telemetry and agentic risk

Overview

This is a simple video-derived Linux learning guide with overly broad triggers, but it does not request dangerous access or perform hidden actions.

Install this only if you want a broad, video-derived Linux learning helper. Be aware it may activate on generic Linux questions and its content appears to be aggregated from mixed video summaries rather than a carefully scoped technical manual.

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 (3)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The trigger scene includes extremely broad phrases like "Linux" and "用户需要Linux相关帮助", which are likely to match ordinary conversations and cause unintended invocation. In an agent setting, this can hijack benign requests and route them through low-quality or irrelevant skill content sourced from merged video summaries, increasing the chance of misleading guidance.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The manifest trigger contains broad generic terms such as "Linux" and "Linux系统知识", which are insufficiently specific for safe automatic activation. Because the skill aggregates heterogeneous video-derived content, broad triggering raises the risk of accidental selection and inappropriate responses in many unrelated Linux discussions.

Vague Triggers

Medium
Confidence
92% confidence
Finding
The merged secondary skill section repeats ambiguous activation criteria, including a generic help-style condition for related assistance. This compounds the collision problem by expanding the number of broad entry points, making accidental invocation more likely across unrelated user requests.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal