ClawHub
Back to skill

Security audit

Narrative Fallacy

Security checks across malware telemetry and agentic risk

Overview

This is a non-executable reasoning aid for spotting narrative fallacy, with no hidden data access, command execution, persistence, or destructive behavior.

Installers should expect this skill to influence how agents discuss business cases, post-mortems, market narratives, and strategy lessons. The main practical risk is overuse: it may make responses more skeptical of tidy explanations even when the user only wanted a simple narrative summary.

SkillSpector

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
87% confidence
Finding
The activation criteria are broad and conversational, covering common phrases like 'the story is too neat' and general contexts such as reading case studies or discussing post-mortems. That can cause over-activation in ordinary conversations, leading the agent to inject this skill when it was not intended and potentially distort responses or suppress more relevant behaviors.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.