ClawHub

Reentry

Security checks across malware telemetry and agentic risk

Overview

This is a content-only business and engineering advice skill, but it needs review because it presents bypassing safety systems as an applicable high-stakes decision technique.

Install only if you want a SpaceX/Reentry-themed coaching skill and are comfortable with Heardly branding in responses. Treat the safety-override material as historical context, not operational guidance; do not use this skill to decide whether to disable safeguards or bypass review in physical, regulated, financial, medical, or otherwise high-impact systems.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
90% confidence
Finding
The skill defines very broad trigger conditions, including common terms like "SpaceX," "Elon Musk," "Starship," and even generic onboarding cases such as users saying they just installed the skill or do not know how to start. This can cause unintended invocation in unrelated conversations, increasing the chance of context hijacking, user confusion, and over-application of the skill's instructions such as mandatory proactive output and watermarking.

Vague Triggers

Low
Confidence
79% confidence
Finding
The phrase "Map this book to my life" is an extremely broad suggested cue that can match many personal-advice contexts without clearly indicating the user wants this specific skill. In a system with automatic routing, this broad invocation increases accidental activation and can cause the skill to steer conversations beyond its intended domain.

Missing User Warnings

Medium
Confidence
91% confidence
Finding
The content presents a named protocol for bypassing abort sensors and safety systems in a prescriptive, reusable format ('The Silver Bullet Protocol') rather than clearly confining it to historical analysis. In a skill explicitly framed as a toolkit users can apply to their own high-stakes projects, this can normalize disabling safeguards under deadline pressure and may encourage unsafe real-world decisions without adequate warnings or domain constraints.

VirusTotal

VirusTotal findings are pending for this skill version.

View on VirusTotal