ClawHub
Back to skill

Security audit

Signal Intelligence Pack

Security checks across malware telemetry and agentic risk

Overview

This is a research-grounding workflow that may run extra searches, but the behavior is disclosed, purpose-aligned, and not privileged.

Install only if you want a broad research preflight skill. For sensitive topics, avoid including secrets in prompts, review which search providers and child skills are available in your environment, and expect possible extra search calls or provider quota use.

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
90% confidence
Finding
The skill’s trigger conditions are very broad, covering most tasks that rely on external information, multi-source grounding, time sensitivity, or narrative risk. In an agent environment, this can cause unintended invocation on many routine tasks, increasing tool usage, complexity, and the chance that downstream subskills perform unnecessary searches or over-collect data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal