Capability Radar

Security checks across malware telemetry and agentic risk

Overview

This is a markdown-only skill that logs capability gaps to local memory so future sessions can improve workflows.

Install this only if you want the agent to write persistent capability-gap notes and let future sessions use them as improvement signals. Avoid recording secrets, private personal details, customer data, or sensitive operational context in those memory entries.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (1)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The skill defines several trigger conditions using broad natural-language concepts such as '做不了', '做错了', and '绕了一大圈才做到', which leaves substantial room for subjective interpretation. In a memory-writing workflow, this can cause over-triggering, noisy logging, and incorrect architectural signals that may drive unnecessary rule or skill changes.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal