企业-中标数据与营收分析

Security checks across malware telemetry and agentic risk

Overview

This skill only guides public bid-award research and report writing, with no executable code, credentials, persistence, or mutation authority.

Install only if you want agents to perform public procurement and bid-award research about companies. Treat cash-flow, customer-dependence, and regional-expansion conclusions as analyst inferences that should be checked against cited public sources.

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
87% confidence
Finding
The activation description is broad enough to trigger on general competitive-intelligence, due-diligence, or customer-analysis queries without tight boundaries. That can cause the skill to run unexpectedly, perform unnecessary web searches, and produce inferred financial or customer-profile claims about a company, increasing privacy, accuracy, and misuse risks.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal