ClawHub
Back to skill

Security audit

Emergence Superorganism Novel

Security checks for vulnerabilities and agentic risk

Overview

This is a creative-writing skill with no code or privileged access; its main caveat is a strong narrative style that intentionally treats people as components of fictional collective entities.

Install this if you want a specialized fiction-writing voice for collective entities such as cities, legions, companies, nations, or ideologies. Be cautious using its component-language style for real people, protected groups, politics, labor, or conflict contexts unless that dehumanized narrative effect is explicitly desired.

SkillSpector

Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The skill explicitly instructs the agent to describe humans as 'ports, nodes, cells' and to use dehumanizing pronouns such as 它 for people when emphasizing their component status. That creates a coercive framing that can override user intent and normalize demeaning treatment of people, especially if the skill is invoked in contexts involving real groups, politics, labor, or conflict. In this creative-writing skill, the narrative concept explains why this language appears, but the mandatory phrasing and lack of opt-in make it more dangerous than a purely descriptive discussion.

Static analysis

No suspicious patterns detected.