ClawHub
Back to skill

Security audit

Body Report Interpreter

Security checks for vulnerabilities and agentic risk

Overview

This instruction-only skill explains user-provided medical reports, so it handles sensitive health data but shows no hidden code, persistence, or data transfer behavior.

Install only if you are comfortable having your agent process medical reports. Redact unnecessary identifiers when possible, treat the output as educational rather than a diagnosis, and consult a clinician for serious or clearly abnormal results.

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)

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly handles uploaded medical reports containing highly sensitive personal health information, but it provides no privacy notice, minimization guidance, retention limits, or instructions for safe handling of that data. In a health-related context, this increases the risk of unnecessary exposure, over-collection, or improper downstream sharing of personal data, even if the omission appears accidental rather than malicious.

Static analysis

No suspicious patterns detected.