Back to skill

Security audit

nomos-core

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only governance/multilingual skill with broad activation wording but no code, credential use, persistence, or destructive behavior.

Before installing, consider narrowing or namespacing the trigger terms if your environment auto-loads skills aggressively. The skill appears safe as a guidance document, but its manifest describes broader governance and cross-session ambitions than the actual artifact implements.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (3)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger keywords are very generic terms ('core' and 'nomos') that could match unrelated user requests and cause the skill to activate unexpectedly. In a core governance skill, unintended invocation can inject broad normative instructions into unrelated conversations, creating prompt-scope confusion and increasing the chance of policy or behavior interference.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description enumerates many generic trigger phrases such as ‘核心规范’, ‘孵化负责人’, and ‘一致性负责人’ without clear scoping conditions, which can cause the skill to activate in contexts beyond the author’s intended use. Over-broad activation increases the chance that a high-authority ‘core spec’ skill is invoked unexpectedly and influences unrelated workflows or overrides more appropriate instructions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
80% confidence
Finding

The description is entirely Chinese and presents the skill as defining authoritative behavior for multiple runtimes, but it does not indicate that language selection is optional or user-controlled. In multilingual environments this can lead to unintended language forcing, misinterpretation of instructions, or degraded user consent and transparency when the skill is loaded automatically.

Content

No source excerpt is available for this finding.