ClawHub

Facebook Pages

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Facebook Pages management skill that can make real page changes only when used with the user's MyBrandMetrics credentials.

Install only if you trust MyBrandMetrics and intend to let an agent manage real Facebook Page content. Use least-privilege credentials, avoid committing tokens or IDs, verify the Page and post/comment IDs before publishing or moderating, and do not override the API base URL unless the destination is trusted.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill documentation describes capabilities that require environment access, file/config reading, and outbound network calls, but it does not declare permissions for those sensitive operations. This creates a transparency and policy-enforcement gap: users or platforms may approve the skill without understanding it can read credentials/config and send data to external services, increasing the risk of unintended secret exposure or unauthorized API usage.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The examples demonstrate operations that can publish posts, create comments, hide comments, and delete comments against live Facebook Pages without any explicit warning, confirmation guidance, or indication that these actions are state-changing. In an agent skill context, copy-pastable examples strongly influence operator behavior, so omission of safety cues increases the chance of accidental modification of production social media content and unintended reputational or moderation impacts.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal