ClawHub
Back to skill

Security audit

AI Knowledge Companion

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Obsidian knowledge-management helper with broad but purpose-aligned note, study, writing, and research workflows.

Install this if you want an English Obsidian study companion and are comfortable letting it create and update files inside the configured vault. Review any proposed deletions, broad exports, reminders, or vault-root changes before approving them.

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 (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description is extremely broad and covers many routine study, writing, research, and vault-maintenance tasks, which creates ambiguous activation boundaries. In agent environments, this can cause the skill to trigger for loosely related requests and take over flows involving file operations, web research, or drafting without clear user intent, increasing the chance of unintended actions or prompt-scope abuse.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The shortcut list includes generic phrases such as 'find', 'polish', 'proofread', 'reading plan', and 'academic updates' that commonly appear in ordinary conversation. This makes accidental or adversarial triggering easier, especially when combined with file-writing and search capabilities, potentially causing the agent to invoke the skill in contexts the user did not intend.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The slug value "shutong-en" includes an explicit language marker suggesting the skill is English-specific. In this manifest file there is no accompanying documentation, opt-in mechanism, or justification showing that the language restriction is optional or required for a region-specific purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The manifest text explicitly describes the skill as an "English knowledge management companion" and the default prompt hard-codes use of "$shutong-en," which indicates a language-specific constraint. There is no indication that users can choose another language or opt into English-only behavior.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.