ClawHub
Back to skill

Security audit

Anki Fusion

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Anki flashcard generator with disclosed PDF, text, and URL inputs, and no bundled code or persistence.

Installers should only provide PDFs, text, or URLs they intend to turn into study cards, and should treat remote pages as untrusted content unless they know the source.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill description is very broad ('Convert any learning material into Anki flashcards') and the workflow accepts many input types, including raw text, PDFs, and web URLs, without clear trigger boundaries or trust constraints. In agent environments, overly broad scope can cause unintended invocation on sensitive or untrusted content, increasing the chance of data overcollection, unsafe processing, or surprise network access.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly supports web page URL input but does not warn users that processing may fetch external content. This can expose users to privacy and security risks such as unintended requests to attacker-controlled URLs, retrieval of sensitive internal resources if the runtime has network access, or ingestion of malicious prompt content from remote pages.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.