ClawHub
Back to skill

Security audit

Pre-Mortem Analyst

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only planning skill for project pre-mortems, with no evidence of code execution, data access, persistence, or hidden behavior.

Review the included examples if you want a fully generic skill, because some examples are specific to named business scenarios. The main practical risk is over-activation on broad risk-related phrases; security-sensitive behavior was not found.

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 invocation description includes broad phrases such as "what could go wrong," "risk analysis," "before we launch," and "project risks," which are common expressions in ordinary conversation and could cause unintended activation. The description does not provide clear scope boundaries or exclusion conditions to distinguish when this skill should or should not trigger.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.