cognitive-bullwhip
Security checks across malware telemetry and agentic risk
Overview
This is a non-executable diagnostic skill that analyzes user-provided agent decision logs and shows no hidden execution, persistence, credential access, or data transfer behavior.
Install only if you are comfortable supplying summarized agent decision history. Remove secrets, customer data, credentials, and unnecessary internal details from logs, and treat the linked paid remediation skills as vendor recommendations rather than neutral requirements.
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.