lofter-fic-writer

Security checks across malware telemetry and agentic risk

Overview

This is a text-only LOFTER fanfiction writing aid; the flagged persona line appears to be sample story material, not hidden agent behavior.

This skill appears safe from an agentic-security perspective. Before installing, consider that it uses bundled fandom samples and is designed to produce high-click fanfiction, so review outputs for originality, platform rules, rating/content boundaries, and fandom norms before posting.

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)

Natural-Language Policy Violations

Medium

Confidence: 91% confidence
Finding: The file begins by imposing a fixed persona, name, body type, and personality traits on the agent without any user opt-in. This is a real prompt-safety issue because it can override user intent, constrain model behavior, and normalize identity/role-locking that may interfere with downstream instructions or create unsafe social-role dynamics.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal