ClawHub
Back to skill

Security audit

safety-critical-patterns

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only coding-guidance skill with no executable behavior, though some triggers are broader than ideal.

Before installing, be aware this skill may appear during some general safety, medical, NASA, robustness, or assertion-related discussions. Its content is advisory coding guidance only; users wanting tighter control should narrow the triggers.

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 trigger list contains generic terms such as 'safety', 'assertions', 'NASA', 'medical', and fragmented phrasing like 'or high-reliability system code' that can match ordinary discussion far outside the intended niche. Overly broad activation increases the chance this skill is invoked unexpectedly, causing prompt/context injection into unrelated tasks and reducing user control over agent behavior.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.