Back to skill

Security audit

obsidian-consulting-notes

Security checks for vulnerabilities and agentic risk

Overview

This skill organizes a user-selected Obsidian consulting-note workspace and has ordinary file-organization risk, but no hidden code, network behavior, credential use, or persistence was found.

Install only if you want an agent to read and reorganize the selected Obsidian consulting-note folder. Run small batches, review the proposed file list carefully before confirming, and keep a backup because broad keyword rules can rename, move, or retag notes incorrectly.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The file naming rules require Chinese prefixes and specify that keywords must be 2-4 Chinese characters, which imposes a language/locale constraint. The document does not provide opt-in, alternatives, or a clear justification that the skill is limited to a Chinese-only environment.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The cleanup flow performs potentially destructive file management actions based on heuristic classification and similarity thresholds, but it does not require an explicit safety warning or strong confirmation immediately before those actions. In a knowledge-base context, false positives can mislabel or relocate valuable notes, causing data loss, confusion, or silent corruption of the user's workspace organization.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The keyword-to-folder mapping is very broad and uses many common business terms, so unrelated notes can be auto-classified into authoritative knowledge-base locations. In this skill, over-inclusive routing can misfile sensitive or irrelevant content, trigger incorrect downstream tagging/splitting behavior, and reduce trust in the resulting note corpus.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The quick judgment logic relies on ambiguous phrases like '问题', '方案', and '模板', which are common across many consulting documents and can cause incorrect prefixing and storage decisions. Because this skill automates document splitting and organization, a weak top-level decision rule can propagate classification errors across many generated MD files.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

L080-L083 将重复处理描述为“其余文件名末尾追加 '_重复' 标记”,这表示实际对象应是文件名;但紧接着又写“使用 replace_in_file 修改文件名中的 YAML title 字段,或直接生成重命名建议”,replace_in_file 只能更新文件内容中的 title,而不是真正重命名文件。随后 L089 又说用户确认后执行“重命名/移动操作”,与前述实现说明形成直接矛盾。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.