ClawHub
Back to skill

Security audit

Soft Pillow - Sleep & dream journal

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Soft Pillow API helper for user-requested sleep and dream queries, with sensitive data access that is expected for its purpose but worth treating carefully.

Install only if you are comfortable giving the agent access to your Soft Pillow sleep, dream, notes, mood, disruption, and related entry data. Keep the API key private, revoke it from the app settings if no longer needed, and avoid asking the skill to retrieve entries containing information you do not want processed by your agent or the Soft Pillow API.

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
  • 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 is explicitly designed to access highly sensitive personal data, including sleep patterns, dreams, mood, disruptions, notes, and activity information, and it does not warn users that this information will be transmitted to a third-party API. Because dream/notes fields can contain intimate or health-adjacent personal details, lack of clear privacy disclosure and consent expectations increases the risk of oversharing sensitive data to an external service.

Static analysis

Detected: suspicious.exposed_secret_literal

File appears to expose a hardcoded API secret or token.

Critical
Code
suspicious.exposed_secret_literal
Location
SKILL.md:52