ClawHub
Back to skill

Security audit

Daily Workflow Manager

Security checks for vulnerabilities and agentic risk

Overview

This is a local workflow-documentation helper that writes project handoff notes, with no evidence of hidden execution, network transfer, or credential use.

Install only if you want the agent to maintain local workflow notes in your project. Choose low-collision trigger phrases, review changes under Docs/ and .workbuddy/, and do not let handoff notes store secrets, tokens, credentials, private personal data, or confidential details that should not be committed or shared.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
89% confidence
Finding
The default trigger phrase "break time" is broad, conversational language that can appear in normal discussion unrelated to this skill. Because the skill performs filesystem reads and writes when triggered, accidental activation could cause unintended document creation or modification without the user's explicit intent at that moment.

Missing User Warnings

Medium
Confidence
86% confidence
Finding
The skill is designed to create and modify multiple project files, but the description does not prominently warn users about this write behavior before activation. In practice, this can reduce informed consent and increase the chance that users invoke the skill expecting a passive summary while it performs persistent changes to the workspace.

Ssd 3

Medium
Confidence
92% confidence
Finding
The handover guidance explicitly tells the agent to record user preferences, decisions, detailed context, and relevant snippets for future AI instances, but it provides no restrictions on secrets, personal data, credentials, tokens, or other sensitive operational details. This creates a realistic risk of persistent sensitive-data leakage into project documentation that may later be exposed to other agents, collaborators, or version control.

Static analysis

No suspicious patterns detected.