Relevance Ai
Security checks across malware telemetry and agentic risk
Overview
This appears to be a legitimate Relevance AI integration, but it gives broad authenticated control over account data without clear built-in limits or confirmation rules.
Install only if you trust Membrane and intend to give the agent delegated Relevance AI access. Use a least-privileged tenant/account where possible, review the exact action or endpoint and request body before any mutating operation, and be especially careful with organization, user, or delete actions.
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
65/65 vendors flagged this skill as clean.