ClawHub
Back to skill

Security audit

Canvora PDF Document

Security checks for vulnerabilities and agentic risk

Overview

The skill provides a coherent Canvora PDF workflow, with expected document sharing and clearly stated generation costs.

Submitted content and source URLs are processed by Canvora, so share only authorized material and avoid confidential information or private access links. Check the page count and credit total; document generation costs 15 credits per page. Separate CLI setup instructions were not included in this package.

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
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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)

The workflow sends user-provided document content to Canvora without a privacy disclosure.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow directs the agent to submit user-provided copy or source-document URLs to Canvora without first explaining that an external service will process them or checking whether the material is appropriate to share. Reports, proposals, and company documents can contain confidential or personal information, making unintended disclosure plausible. Canvora processing is central to the advertised functionality, which reduces suspicion of malicious exfiltration but does not establish informed authorization to upload sensitive content.

Content

No source excerpt is available for this finding.