Flash Thoughts

Security checks across malware telemetry and agentic risk

Overview

This is a coherent local note-taking skill, but its show command can read Markdown files outside the intended notes folder if given path-like input.

Install only if you are comfortable with a plaintext local notes tool. Avoid storing secrets or sensitive information, use an explicit private storage directory, and fix or avoid the show command with anything other than strict YYYY-MM-DD dates until path validation is added.

SkillSpector

By NVIDIA

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

Low

Confidence: 90% confidence
Finding: The README clearly describes capturing and storing user thoughts in daily local files, but it does not explicitly warn users that their inputs are persisted on disk. For a note-taking skill this behavior is expected, so this is not malicious, but the lack of a clear privacy/persistence notice can still lead users to record sensitive information they did not realize would be retained.

Vague Triggers

Medium

Confidence: 88% confidence
Finding: The trigger phrases are broad, conversational, and overlap with ordinary speech such as '记下来' or '突然想到', which can cause unintended invocation. If auto-triggered, the skill could write user content to disk or perform searches when the user did not explicitly intend to use this skill, creating privacy and integrity risks.

VirusTotal

62/62 vendors flagged this skill as clean.

View on VirusTotal