ClawHub
Back to skill

Security audit

Agente Literatura

Security checks across malware telemetry and agentic risk

Overview

This is a Portuguese literature tutoring skill with broad activation wording but no code execution, credential access, persistence, or sensitive data handling.

Install it if you want a Portuguese-first conversational study aid for FUVEST literature. Be aware it may activate broadly around literature, authors, reading, or related study discussions, so users with many specialist skills may want clearer routing preferences.

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
95% confidence
Finding
The skill’s activation criteria are very broad, including whenever Antonio mentions any work, author, literary movement, wants to talk about reading, or when the orchestrator merely detects an 'opportunity' to connect with literature. This can cause unintended invocation outside the user’s actual intent, leading to context hijacking, unnecessary interference with other skills, and degraded routing reliability.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal