ClawHub

Social Content

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only social media planning skill with limited, disclosed local context use and no evidence of hidden execution, credential access, persistence, or autonomous posting.

Reasonable to install for social media planning. Before using it, make sure local product marketing or brand voice files do not contain secrets or information you would not want reflected in draft posts, and review any scraping or third-party research-tool suggestions against platform rules and your account-safety expectations.

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
87% confidence
Finding
The trigger description is extremely broad and includes many common phrases like 'social media,' 'what should I post,' and 'engagement,' which can cause the skill to activate for loosely related requests. Over-broad routing is dangerous because it increases the chance of unintended invocation, causing the agent to apply social-content instructions and possibly access additional local context files when the user did not intend that scope.

Missing User Warnings

Low
Confidence
90% confidence
Finding
The skill instructs the agent to automatically read project-local files containing product marketing and brand voice context without first obtaining user awareness or consent. This is risky because it expands the data the agent may access during a social-content task, potentially exposing sensitive internal strategy, positioning, or brand guidance beyond what the user explicitly provided.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The evaluation explicitly rewards the skill for triggering on vague, casual phrasing rather than clear social-content intent. That encourages overly broad routing behavior, which can cause the wrong skill to activate for loosely related requests and increases the chance of prompt/context leakage or inappropriate task handling across adjacent domains.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal