ClawHub
Back to skill

Security audit

Daily Questions

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed daily questionnaire that stores user and agent preferences, with privacy considerations around Telegram and memory files but no evidence of hidden or malicious behavior.

Install only if you are comfortable with a scheduled routine asking personal preference questions over Telegram and storing the answers in USER.md and SOUL.md for future agent behavior. Avoid sharing sensitive information, and periodically review or delete those files if your preferences change.

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 (2)

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill explicitly collects personal information and agent-preference data and persists it into USER.md and SOUL.md, but it provides no notice, consent step, retention policy, or guidance on limiting sensitive data. This creates a real privacy risk because users may disclose personal details without understanding they will be stored long-term and reused to shape future agent behavior.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The workflow requires sending questions and receiving answers over Telegram, a third-party messaging platform, without warning the user that their responses will transit and potentially persist outside the local system. Because the questions are designed to elicit personal preferences and behavioral information, the platform transmission materially increases privacy exposure.

Static analysis

No suspicious patterns detected.