agent-bom runtime
Security checks across malware telemetry and agentic risk
Overview
The available scan data is clean and the inspected skill instructions appear purpose-aligned, though some maintainer workflows can run high-impact local or admin commands when explicitly invoked.
Install or use this only in a trusted ClawHub development context. Before running moderation or review-helper commands, verify the target repo, account, and auth token, and consider using the helper's no-yolo option if full-access nested review is not needed.
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.