Smart Daily Report by YQG

• Outcome: Pass
• Latest audit: May 29, 2026 at 8:33 PM UTC
• Version:
  3.0.2

Overview

This is a report-writing skill whose access to work history, tasks, calendars, and optional exports is disclosed and aligned with its purpose.

Install this only if you want an agent to summarize your work from repositories and connected productivity tools. When using it, specify the exact date range, projects, data sources, and export destination, and avoid broad home or desktop scans unless you intend to include all discovered projects.

SkillSpector

By NVIDIA

Vulnerability Patterns

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

Findings (5)

Vague Triggers

Medium

• Confidence: 90% confidence
• Finding: The activation condition 'Any request to summarize work activity' is overly broad and can trigger the skill during ordinary conversation, causing it to begin gathering project, task, or calendar data without sufficiently specific user intent. In this skill, over-triggering is more dangerous because later steps instruct scanning local directories and aggregating personal work data.

Vague Triggers

Medium

• Confidence: 86% confidence
• Finding: Several triggers like 'What did I work on' or '我做了什么' are generic enough to match normal reflective conversation rather than a clear request to inspect local activity sources. Because the skill is authorized to collect from repositories, task tools, and calendars, accidental invocation could expose or process more data than the user expected.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill instructs scanning common locations like workspace, home, and desktop for project directories, which can enumerate and inspect local data without an explicit notice or consent boundary. In context, this is especially risky because those paths may contain unrelated private repositories, confidential client work, or sensitive filenames not needed for the user's immediate request.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: Aggregating calendar entries, completed tasks, and project history can reveal sensitive work patterns, meeting subjects, project names, and personal productivity details, yet the skill provides no warning or consent prompt. Combining multiple sources increases sensitivity beyond any single dataset and can expose private or regulated business information in the generated report.

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The export options include writing to external services and files without warning that the generated report may persist sensitive project details outside the current chat context. This creates disclosure risk because reports may contain internal commit summaries, meeting information, or task metadata that are stored, shared, or synced elsewhere.

VirusTotal

62/62 vendors flagged this skill as clean.