ClawHub
Back to skill

Security audit

Agent Daily Briefing

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed daily-briefing workflow, but users should configure delivery, data sources, and memory logging carefully because it can summarize personal information into messaging channels.

Install only if you are comfortable with your agent summarizing calendar, task, location, pending-item, and optional news context. Configure BRIEFING.md with private delivery channels, disable sections you do not need, avoid shared Discord or Telegram destinations for personal data, and use the advanced memory logging only if you want persistent briefing history.

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 (3)

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill encourages compiling and delivering a briefing from calendar, tasks, memory, weather, and optional news sources, but it does not clearly warn that this may access and transmit personal or sensitive information. Because the output is sent to a configured messaging channel, users may unknowingly expose schedules, locations, pending work items, or other private context to third-party platforms or shared destinations.

Vague Triggers

Medium
Confidence
95% confidence
Finding
The on-demand trigger phrase "Give me my daily briefing" is broad and does not define authorization, channel, or confirmation boundaries. In an agent environment with multiple users, shared channels, or prompt-driven automations, this can cause the agent to compile and transmit sensitive calendar, task, pending-item, or news context to an unintended recipient or at an unsafe time.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The file explicitly instructs the agent to log briefing engagement to `memory/briefing-log.json` and to read/write dated memory files as part of a continuous task-tracking loop, but it provides no notice, consent model, retention guidance, or limits on what personal data may be persisted. In this skill context, the stored content can include calendar activity, tasks, travel details, and behavioral patterns, which creates a meaningful privacy risk through silent accumulation of sensitive user data over time.

Static analysis

No suspicious patterns detected.