AI Daily Briefing

• Outcome: Pass
• Latest audit: May 28, 2026, 4:48 AM
• Version:
  1.0.0

Overview

This is an instruction-only daily briefing skill that reads relevant productivity context but does not install code, persist itself, exfiltrate data, or mutate files.

Install only where the agent is allowed to read your to-do list, recent meeting notes, memory files, preferences, and connected calendar data. Use explicit prompts like "daily briefing" in shared contexts, and avoid keeping sensitive notes in the referenced folders if they should not appear in a briefing.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (5)

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The trigger phrases include broad, natural-language prompts such as "what do I need to know?", "start my day", and "give me the rundown," which can easily appear in ordinary conversation. That makes accidental invocation plausible, causing the skill to gather and summarize sensitive workspace data like tasks, meeting notes, memory files, and calendar contents when the user may not have intended to run this skill.

Missing User Warnings

Medium

• Confidence: 96% confidence
• Finding: The skill explicitly instructs the agent to read from todo lists, meeting notes, memory files, and calendar data, but the user-facing description does not clearly warn that personal and potentially sensitive information will be accessed. This reduces informed consent and increases the chance that users trigger the skill without realizing the breadth of data it may aggregate and expose in a single response.

Vague Triggers

Medium

• Confidence: 93% confidence
• Finding: The suggested invocation phrases are broad natural-language expressions like "start my day" and "give me the rundown," which can plausibly appear in ordinary conversation. That increases the risk of accidental or ambiguous activation, causing the skill to trigger when the user did not intend to access briefing behavior or connected work data.

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The quick-start instructs users to simply say "briefing" or similar phrases without defining boundaries for when the skill should activate or what context is required. In an agent environment, this lack of scope can cause the skill to intercept unrelated requests or expose synthesized information from calendars, tasks, and meeting notes in situations where the user did not explicitly request that data.

Missing User Warnings

Medium

• Confidence: 88% confidence
• Finding: The file encourages connecting calendars and using to-do items derived from meeting notes, but it does not warn users that the skill may surface sensitive scheduling details, action items, conflicts, or meeting-derived context. Because the skill aggregates personal productivity data, missing privacy disclosures can lead to unintentional exposure of confidential business or personal information in shared or unsafe contexts.

VirusTotal

62/62 vendors flagged this skill as clean.