ClawHub
Back to skill

Security audit

nomos-core

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only governance and multilingual guidance skill with no commands, credential access, persistence, or data exfiltration behavior found.

Reasonable to install if you want this governance-style guidance, but review the broad activation wording and consider narrowing triggers if your environment auto-loads skills aggressively.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger keywords are very generic terms such as "core" and "nomos", which can cause the skill to activate in unrelated conversations. Overbroad activation increases the chance that governance text or behavioral instructions are injected into contexts where the user did not intend to invoke this skill, creating prompt-routing confusion and possible policy interference.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The manifest description defines many broad trigger phrases such as '核心规范', '孵化负责人', and '一致性负责人' without clear activation constraints, making it easy for the skill to be invoked in contexts beyond its intended scope. Because this is a core-spec skill that propagates behavior across multiple runtimes and downstream '负责人' agents, accidental or overly broad activation could cause unintended inheritance of authoritative instructions at scale.

Static analysis

No suspicious patterns detected.