ClawHub
Back to skill

Security audit

NOUS

Security checks for vulnerabilities and agentic risk

Overview

NOUS is an instruction-only thinking-format skill that changes response style but does not request tools, files, credentials, network access, or persistence.

Install this only if you want the assistant to adopt NOUS's visible-thinking response format broadly. It appears low risk from a security perspective, but it may be intrusive for everyday short answers unless invoked selectively.

A.I.G

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

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
97% confidence
Finding
This markdown skill description defines invocation behavior with the phrase 'User sends anything,' which is maximally broad and overlaps with ordinary conversation. It does not provide trigger constraints, scoped contexts, or negative examples to clarify when the skill should or should not activate.

Static analysis

No suspicious patterns detected.