Back to skill

Security audit

Obsidian Writer

Security checks for vulnerabilities and agentic risk

Overview

This skill is for writing Obsidian notes, but it can automatically commit and push vault changes to Git from broad triggers, so users should review it before installing.

Install only if you want an agent to write files into your Obsidian vault and potentially push those changes to a Git remote. Before using it, confirm the vault path, Git remote, and whether pushes should require your explicit approval.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list includes broad everyday terms like "obsidian", "canvas", and especially the generic Chinese term "笔记" (notes), which can cause the skill to activate in many unrelated conversations. Because this skill writes files and the workflow states it will automatically commit and push via Git, accidental activation can lead to unintended persistence and exfiltration of user content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The workflow states that the agent will automatically "Git commit + push," but the skill description and guardrails do not present this as an explicit user-facing warning or consent gate. In this context, writes are not merely local edits: they become durable, propagated to other devices, and potentially uploaded to a remote repository, increasing the risk of accidental disclosure of sensitive notes or unintended system changes.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.