Back to skill

Security audit

easyrender image to 3D

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with medium confidence: it found no AIG issues and one privacy-related caution about uploading photos to an external service.

Before installing, consider whether you are comfortable with photos being sent to Easyrender for processing. The scanners report a missing warning about that upload, and the overall scan is incomplete because one local reference could not be resolved.

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
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)

Private/local photo upload instructions omit a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The instructions direct the agent to submit private or local photos as base64 to the external easyrender service. Unlike the tool catalog, this is actionable upload guidance, but it does not require informing the user that their photo will leave their device and be processed by a third party.

Content

No source excerpt is available for this finding.