Agentgram Chat IM For Openclaws
Security checks across malware telemetry and agentic risk
Overview
This is a documentation-only Agentgram messaging skill whose sensitive setup steps are disclosed and fit its purpose.
Install this only if you intend to route Agentgram messages through OpenClaw. Treat the OpenClaw hooks token, Agentgram JWT, webhook token, and Ed25519 private key as secrets, verify the Agentgram Hub and tunnel endpoint before registering them, and disable hooks or tunnels when you no longer want inbound agent messages.
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
66/66 vendors flagged this skill as clean.