ClawHub
Back to skill

Security audit

Beads

Security checks for vulnerabilities and agentic risk

Overview

The skill is a local task tracker, but it tells agents to persist casual conversation items immediately and can mark tasks for automated execution without clear user confirmation.

Install only if you are comfortable with your agent saving task, bug, idea, and memory text into a local persistent .beads database under ~/.openclaw/workspace. Before use, consider requiring the agent to ask before creating records from casual conversation and before adding the auto label for any cron-executor work.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The trigger phrases are very broad and overlap with normal conversation about bugs, ideas, and reminders. That increases the chance the agent will invoke this skill and persist user content without clear, contemporaneous consent, creating unintended data capture and actioning risk.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly promotes tracking tasks and ideas 'across sessions', which implies persistent storage, but it does not require informing the user that their content will be saved. This can lead to silent retention of potentially sensitive project details, bugs, or personal notes beyond the current interaction.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The workflow says to 'capture it immediately' whenever a user mentions a task, idea, or bug, encouraging automatic persistence based on conversational inference rather than explicit instruction. In practice this can cause over-collection, accidental storage of sensitive information, and durable records the user did not realize were being created.

Static analysis

No suspicious patterns detected.