ClawHub
Back to skill

Security audit

LATAM Timezone Briefing

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed offline morning-briefing skill, with only a caution that casual greetings may trigger it and reveal local agenda details.

Install only if you are comfortable with the agent reading ~/centriqs/briefing/config.md and agenda.md when producing briefings. Avoid storing full tax identifiers or confidential meeting details there, and consider using explicit commands like "briefing hoy" instead of casual aliases if accidental activation would be a problem.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The skill advertises very broad natural-language triggers such as "buenos días" and "qué hay hoy", which are common conversational phrases and can cause the skill to activate unintentionally in ordinary chats. In an agent environment, this can lead to confusing behavior, unexpected scheduled-style outputs, or accidental invocation of downstream integrations when the user did not explicitly request this skill.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The activation aliases include very common conversational phrases such as "buenos días", "qué hay hoy" and similar variants, which can cause the skill to trigger when the user did not intend to invoke it. In this skill's context, unintended activation could expose private agenda content or fiscal reminders in the wrong conversation context, especially because the skill is designed to pull potentially sensitive local data.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.