ClawHub
Back to skill

Security audit

Canvora LinkedIn Carousel

Security checks for vulnerabilities and agentic risk

Overview

The skill fits its purpose of creating LinkedIn visuals through Canvora, with expected content sharing and disclosed credit costs.

Use content and brand assets you are comfortable sending to Canvora. Generation spends account credits; the skill states 15 credits per carousel slide. Review the separate Canvora setup instructions and finished visuals before publishing.

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-authored content to Canvora without a privacy disclosure.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow instructs the agent to pass an existing post or newsletter section through canvora generate --input "$POST_TEXT" for server-side processing. Although Canvora is named, the skill does not warn that the user's text will leave the local environment and be processed by a third-party service, which matters for unpublished or confidential material.

Content

No source excerpt is available for this finding.