ClawHub
Back to skill

Security audit

Daily Recommend

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed daily recommendation helper with local preference tracking, and its behavior fits its stated personalization purpose.

Install this if you want scheduled Chinese-language literature and arts recommendations. Before enabling the Cron schedule, confirm the notification frequency is acceptable and remember that preference signals will be stored locally in the workspace memory file for personalization.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly records user reactions and preference signals to a workspace file, but it does not tell the user this persistence will occur, what data will be stored, or how long it will be retained. Behavioral preference tracking can reveal sensitive interests and reading habits over time, so silent storage creates a privacy and consent risk even if the feature is intended for personalization.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The description and example trigger phrases are entirely Chinese and imply the skill operates in that language by default. Because no language choice, opt-in, or justification for a Chinese-only locale is provided, this can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.