Smartlead
Security checks across malware telemetry and agentic risk
Overview
The Smartlead skill is mostly coherent, but its setup helper can enable unreviewed local plugin code and configure webhook-triggered agent activity with account access.
Install only if you trust the Smartlead CLI and have reviewed the referenced openclaw-smartlead plugin source. Before enabling webhooks, set a strong webhook secret, confirm the endpoint is not publicly triggerable without authentication, and require explicit approval for lead, campaign, webhook, delete, or raw API 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
64/64 vendors flagged this skill as clean.