Learning Notes Explorer

Security checks across malware telemetry and agentic risk

Overview

No artifact-backed suspicious behavior was found; this is a personal notes search tool, so installing it means letting it read and surface your local learning notes.

This skill appears benign and purpose-aligned. Before installing, check that the notes directory points only to notes you want the agent to read, and be aware that search or synthesis answers may include excerpts from those notes.

VirusTotal

No VirusTotal findings

View on VirusTotal

Risk analysis

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

#
ASI06: Memory and Context Poisoning
Low
What this means

Private learning notes may be read and quoted back when the skill is used.

Why it was flagged

The handler loads local note content into an in-memory index for search. This is expected for the skill’s purpose, but it means personal notes can be retrieved and included in responses.

Skill content
self.notes_dir = notes_dir or os.path.expanduser("~/.openclaw/notes") ... with open(notes_file, 'r', encoding='utf-8') as f: data = json.load(f)
Recommendation

Use it only with note folders you are comfortable exposing to the agent, and confirm the configured notes directory before relying on it.

#
ASI04: Agentic Supply Chain Vulnerabilities
Info
What this means

You have less external information about who maintains the skill or where to verify it.

Why it was flagged

The package has limited provenance metadata. No risky install commands or dependencies are shown, but users have less context for deciding whether to trust the code.

Skill content
Source: unknown; Homepage: none
Recommendation

Review the packaged files and owner information before installing, especially because the skill reads personal notes.