Morning Note

• Outcome: Pass
• Latest audit: Jun 17, 2026 at 2:46 AM UTC
• Version:
  1.0.0

Overview

This skill coherently generates investment morning notes, with disclosed local report saving and optional IMA archiving that users should understand before use.

Install only if you are comfortable with investment summaries being written under the workspace and potentially archived to IMA. Avoid including sensitive holdings, proprietary watchlists, or strategy notes unless you understand who can access the local files and IMA knowledge base, and prefer confirming or disabling archive behavior for ambiguous or scheduled runs.

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 (4)

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The README states that reports are automatically archived to an IMA knowledge base, but it does not disclose retention, visibility, or whether sensitive financial content may persist outside the immediate session. For an investment-reporting skill, the generated content can include holdings, watchlists, and strategy-relevant signals, so silent external persistence creates a real confidentiality and privacy risk.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: The README says reports are written to a persistent local path but does not warn users that potentially sensitive financial summaries will remain on disk after execution. In this context, saved reports may expose portfolio details, watchlist names, or market views to other local users, backups, or downstream tooling that accesses the filesystem.

Vague Triggers

Medium

• Confidence: 94% confidence
• Finding: The trigger phrases are broad and include common terms such as “早报”, “morning note”, and “今日概览”, which can match ordinary user requests and cause the skill to activate unexpectedly. In this skill, unintended activation is more concerning because it can read workspace reports, query external financial data sources, write files, and later sync content to an external knowledge base, increasing the chance of accidental data access or persistence.

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill explicitly writes a report to the working directory and later syncs a summary into the IMA knowledge base, but it provides no user-facing notice, consent step, or disclosure about retention and external sharing. In a financial-reporting context, the generated content may include portfolio movements, watchlists, and other sensitive investment information, so silent persistence and synchronization create a meaningful confidentiality and privacy risk.

VirusTotal

62/62 vendors flagged this skill as clean.