ClawHub
Back to skill

Security audit

OnlyBaby

Security checks for vulnerabilities and agentic risk

Overview

The skill is a simple Markdown-only helper for summarizing user-provided mum and baby logs, with no hidden execution or persistence, but its medical-style verdicts should be treated cautiously.

Install only if you want a structured summary of specific contraction and baby-log JSON files. Do not rely on its 'safe' or 'healthy' labels as medical advice; contact a midwife, OB, paediatrician, or emergency service for urgent symptoms, uncertainty, or any red flags.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill defines concrete medical verdicts such as 'Mum safe', 'Seek care', 'Baby healthy', and 'Concern' before clearly establishing that the output is only supportive guidance and not medical advice. In a health-context skill, users may anchor on these labels as authoritative triage, which can delay urgent care or falsely reassure them, especially because the warning appears only at the end as a caveat.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.