AgentClear

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed paid API proxy skill that can send selected payloads to AgentClear and upstream providers and spend account credits, with no hidden or destructive behavior found.

Install only if you are comfortable letting AgentClear route selected requests to third-party API providers and charge your AgentClear credits per call. Use a revocable key, review service price and trust details before calls, and avoid sending secrets, regulated data, or confidential files unless the chosen upstream provider is approved.

SkillSpector

By NVIDIA

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
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

Findings (1)

Missing User Warnings

Medium

Confidence: 93% confidence
Finding: The README promotes proxying API calls with automatic billing but does not clearly warn that prompts, files, or other user-supplied data may be transmitted to third-party services and may incur real charges. In an agent skill context, this omission is risky because users may assume local or trusted execution while the agent can instead send sensitive data externally and spend account credits.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal