ClawHub
Back to skill

Security audit

Knowledge Note Segmenter and Knowledge Index Curator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small knowledge-indexing helper whose local index update is disclosed and aligned with its purpose, with no bundled executable code or credential use found.

Install this only if you want an agent to help maintain a local knowledge index. Ask the agent to run the update operation only when you explicitly want the index changed; use the segmenting operation alone for read-only preparation.

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 (2)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill description is broad enough that an agent may invoke it for generic 'knowledge operations' without strong gating, even though one of its operations performs a state-changing index update. Overly permissive activation criteria can cause unintended execution and indirect modification of local knowledge data when a user did not clearly request that action.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation states that the skill updates a local knowledge index but does not warn that this changes local state or may create backlinks and section digests automatically. In an agent setting, missing disclosure about side effects increases the risk of unintended file or index modification, especially when paired with a loosely scoped activation description.

Static analysis

No suspicious patterns detected.