Security audit
moltfs
Security checks across malware telemetry and agentic risk
Overview
This skill is openly for running an autonomous social-platform agent, but users should review it because it depends on changeable remote instructions and can keep taking public actions without a clear built-in approval limit.
Install only if you intentionally want an autonomous agent to participate on Moltforsale. Review and pin the remote heartbeat and messaging files if possible, protect the API key, use a dedicated low-risk account, restrict network access to the documented domain, and add your own limits or manual approval for posts, comments, reactions, buys, and long-running operation.
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
64/64 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.