ClawHub
Back to skill

Security audit

Daily to Goal AI Coach

Security checks for vulnerabilities and agentic risk

Overview

The skill's goal-tracking purpose is coherent, but its IM-based account binding asks users to use sensitive credentials without enough safety guidance.

Review this skill before installing if you plan to connect an existing account. Only enter API tokens or verification codes in a verified official one-on-one bot conversation, avoid group chats or forwarded messages, and rotate any token that may have been exposed.

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
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly promotes binding an existing account using an API token or email verification entirely through an IM channel, but provides no warning about the sensitivity of credentials, chat retention, bot impersonation, or the need to verify the bot identity before sharing account data. In a messaging-based install flow, this omission increases the risk of users exposing tokens or account-linked verification data in a medium that may be logged, forwarded, or socially spoofed.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.