Security audit
Requirements Traceability TraceMap
Security checks across malware telemetry and agentic risk
Overview
This is a straightforward QA traceability skill that produces reports from user-provided requirements, tests, and code evidence without hidden execution or privileged behavior.
Safe to install for requirements traceability and QA reporting. Only provide documents, repositories, diffs, configs, prompts, and test evidence that you intend the agent to review, and treat generated release recommendations as advisory rather than an automatic approval decision.
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
53/53 vendors flagged this skill as clean.
Static analysis
No suspicious patterns detected.