ClawHub
Back to skill

Security audit

Daily Review Assistant

Security checks for vulnerabilities and agentic risk

Overview

The skill’s stated purpose is coherent, but it executes an unbundled workspace Python script and can send reports by email, so users should review the local script and email configuration before use.

Install only if you trust the workspace’s stock-analysis/daily_review.py file. Before using --email, inspect the email_config.json recipient settings and use an SMTP app password or authorization code rather than an account password.

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)

Natural-Language Policy Violations

Low
Confidence
67% confidence
Finding
The skill name is presented in Chinese while the operational description is in English, but the manifest does not clarify intended user language, locale, or whether language selection is supported. This can indicate an implicit language constraint or inconsistent locale handling without explicit user opt-in.

Missing User Warnings

Low
Confidence
87% confidence
Finding
The manifest explicitly advertises optional email sending, which implies outbound data transmission, but it provides no user-facing notice about what content may be sent, to whom, or under what trigger. In a reporting skill that may include market analysis or user-derived content, this creates a transparency and consent gap that could lead to unintended disclosure.

Static analysis

No suspicious patterns detected.