ClawHub

dropspace-content-engine

Security checks across malware telemetry and agentic risk

Overview

This skill openly describes an autonomous social-media posting pipeline, and its account-impacting behavior is aligned with that purpose.

Install only if you want automation that can schedule or publish through connected social accounts. Use scoped API keys, keep .env out of source control, review the GitHub project before npm install, start with test or low-risk accounts, and confirm a draft or review workflow before enabling nightly live scheduling.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill description is broad enough to match routine requests like managing social media or setting up posting, which can cause the agent to invoke a high-autonomy pipeline in situations where the user may not expect analytics collection, AI-generated content creation, or external account actions. In this context, over-broad triggering is more dangerous because the skill can schedule posts and persist strategy data, so accidental invocation can lead to unintended actions on connected accounts.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill advertises automated analytics pulling, AI generation, scheduling, and persistent strategy notes without prominently warning that it can take external actions on user-linked accounts and retain learned data across runs. That omission increases the chance users will authorize or invoke the skill without informed consent, which is especially risky here because the pipeline can autonomously publish content and build on prior engagement data over time.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal