Security audit
multi-capability-bug-closure
Security checks across malware telemetry and agentic risk
Overview
This skill is a non-executable workflow guide for evidence-based bug investigation using source code, read-only database checks, logs, and platform queries.
Install only if you want agents to investigate bugs using real operational evidence. Because the workflow may read databases, logs, and business platform records, use it in environments where those tools are already authorized and limit queries to the relevant issue, time window, and objects.
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.
Static analysis
No suspicious patterns detected.