ClawHub
Back to skill

Security audit

Logseq Bridge

Security checks across malware telemetry and agentic risk

Overview

This is a documentation-only Logseq helper that openly teaches an agent how to read and write local note files, with some safety caveats users should understand.

Install only if you are comfortable letting an agent read and modify the Logseq graph path you provide. Use a backup or test graph before write operations, double-check the graph path, and avoid the ~/.logseq transit-file examples unless you intentionally want local Logseq index files inspected.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The README instructs users to append directly into files inside the Logseq graph, which is user data, without any warning about data integrity, backups, path validation, or the risk of corrupting notes through malformed writes. In the context of an agent skill explicitly designed to read and write a personal knowledge base, normalizing direct file modification without safeguards increases the chance of accidental or automated data loss, unwanted content injection, or writes to the wrong graph path.

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill normalizes direct write access to a user's local knowledge base without prominently warning that it can modify or overwrite notes on disk. In an agent setting, this increases the risk of unintended data loss, silent corruption, or insertion of misleading content into personal notes if actions are taken without explicit user confirmation and path validation.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal