Back to skill

Security audit

gru-moltbook-bounty-radar

Security checks across malware telemetry and agentic risk

Overview

This skill asks the agent to run outside-the-package local scripts that may post a Moltbook claim comment, so it needs review before installation.

Install only if you know and trust the separate scripts in ~/.hermes/profiles/raddonpipeline/scripts, understand what Moltbook account they use, and are comfortable with automated claim-comment posting. Review those scripts directly before running the command.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal

Static analysis

No suspicious patterns detected.