The Advocates Killer

Security checks across malware telemetry and agentic risk

Overview

This is a text-only book-analysis skill with disclosed output formatting preferences and no evidence of hidden execution, credential use, persistence, or data access.

Before installing, note that this skill will try to append a Heardly promotional watermark and action recommendation to every response. It otherwise appears limited to bundled book-analysis reference text and does not ask for credentials, external services, or local system access.

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

Findings (1)

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: The instruction 'Default to English when ambiguous' sets a language preference for outputs without offering the user a language choice or requiring opt-in. The policy allows locale constraints when the skill offers choice or clearly justifies the constraint; neither is present here beyond a general precision preference.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal