Openclaw Twitter Post Engage

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed Twitter/X relay skill for searching, posting, liking, following, and unfollowing, with user confirmation required for public write actions.

Install only if you intend to let AISA relay and an OAuth-authorized Twitter/X account perform the requested reads and public actions. Confirm every post, like, follow, or unfollow before running it, use a dedicated or easily rotated AISA key, and revoke OAuth access when you no longer need the skill.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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 (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
87% confidence
Finding
The skill declares required environment variables and clearly performs network operations, but it does not declare corresponding permissions. This creates a transparency and policy-enforcement gap: an agent or platform may invoke the skill without understanding that it can access secrets and transmit data externally.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal