ClawHub
Back to skill

Security audit

DeepRead Insurance Documents

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed, instruction-only DeepRead integration for processing insurance documents, but users should understand that selected claim files are sent to DeepRead’s external API.

Install only if you are comfortable sending selected insurance documents to DeepRead for processing. Before using it with production claims or EOBs, verify DeepRead’s privacy, retention, and compliance terms, use a dedicated rotatable API key, and avoid uploading documents your organization has not approved for third-party processing.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Transmission

Medium
Category
Data Exfiltration
Content
### cURL

```bash
curl -s -X POST https://api.deepread.tech/v1/process \
  -H "X-API-Key: $DEEPREAD_API_KEY" \
  -F "file=@claim.pdf" \
  -F 'schema={"type":"object","properties":{"claim_number":{"type":"string","description":"Claim number"},"policy_number":{"type":"string","description":"Policy number"},"claimant_name":{"type":"string","description":"Claimant name"},"date_of_loss":{"type":"string","description":"Date of loss"},"loss_type":{"type":"string","description":"Type of loss"},"estimated_damages":{"type":"number","description":"Total damages"},"status":{"type":"string","description":"Claim status"}}}'
Confidence
97% confidence
Finding
This skill instructs the agent to upload full insurance claim PDFs to a third-party endpoint, which can contain highly sensitive personal, financial, medical, and claims data. Even though the exfiltration is part of the product's intended function, it is still a real security and privacy risk because the skill promotes transmitting raw documents off-platform before any demonstrated minimization or local redaction, and the broader context includes especially sensitive insurance/EOB content.

Static analysis

No suspicious patterns detected.