ClawHub
Back to skill

Security audit

Knowledge Management System

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-methodology skill that gives knowledge-management templates and workflows without hidden execution or persistence behavior.

Safe to install for documentation and knowledge-base planning. Because the templates discuss internal processes and access requirements, document credential locations and access procedures rather than putting passwords, tokens, or private keys into generated docs.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • 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
Findings (2)

Session Persistence

Medium
Category
Rogue Agent
Confidence
80% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 616)May include surrounding context.

failed_search: threshold: "Same search term fails 5+ times/week" action: "Flag as gap, create task to write missing doc"

text

### Knowledge-Powered Chatbot Design

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The 'Natural Language Commands' section defines activation phrases such as 'Review KB health' and 'Design our KB structure' as plain conversational requests without any scoping, invocation boundary, or exclusion examples. Because these phrases resemble normal collaboration language, the skill could be invoked unintentionally during routine discussion.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.