ClawHub
Back to skill

Security audit

Daily Briefing Hub

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed daily-briefing helper that aggregates connected personal/work sources, with privacy-sensitive behavior that users should configure carefully.

Install only if you are comfortable with an assistant summarizing connected calendar, email, task, GitHub, and news sources. Before enabling recurring delivery, choose the sources and destination channel deliberately, especially for shared Slack, Discord, Telegram, or WhatsApp spaces.

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
  • 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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill is explicitly designed to collect, summarize, and deliver potentially sensitive information from email, calendars, tasks, and messaging channels, but it provides no explicit privacy warning, consent flow, or safeguards around destination channels. This is dangerous because briefings may contain personal, corporate, or confidential content that could be sent to insecure or shared platforms such as Slack, Telegram, WhatsApp, or Discord.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill advertises very broad natural-language trigger phrases such as generic requests for summaries or briefings, which can cause unintended invocation when a user meant a narrower action. Because this skill aggregates data from multiple sensitive sources, accidental activation increases the chance of over-collecting and exposing calendar, email, task, and news data in contexts the user did not intend.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.