agent-bom discover gcp
Security checks across malware telemetry and agentic risk
Overview
This is a disclosed, read-only GCP inventory skill that uses local GCP credentials for cloud discovery but does not show hidden execution, persistence, telemetry, or resource mutation.
Install only if you are comfortable letting the skill use your existing GCP authentication to read inventory metadata from approved projects. Use read-only, scoped, preferably short-lived credentials, choose the output path yourself, and review the generated inventory because cloud metadata can still be sensitive even when credential values are redacted.
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.