Security audit

obsidian-doc-workflow

Security checks for vulnerabilities and agentic risk

Overview

This skill is a structured Obsidian documentation workflow that may edit or move vault documents, but its behavior is disclosed, purpose-aligned, and not secretly privileged.

Install this only for an Obsidian vault where you are comfortable with an agent creating, updating, and moving Markdown documentation. Review archive/move actions before applying them, and adjust the language convention if your vault should not be English-primary.

A.I.G

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

SkillSpector

Vulnerability Patterns

Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (6)

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: The instruction "All documents use English primarily; Persian content is translated/summarized in English" imposes a language policy rather than offering a choice. This is a natural-language policy violation because it forces a specific language/locale behavior without user opt-in or a documented region-specific justification.

Natural-Language Policy Violations

Medium

Confidence: 95% confidence
Finding: The Chinese instruction states that all documents should primarily use English and that Persian content must be translated or summarized in English. This is the same language-policy constraint expressed in another locale and still lacks user choice or a clearly justified compliance reason.

Vague Triggers

Low

Confidence: 77% confidence
Finding: The section begins with `Can you add uppercase filename?` followed by `No. Use canonical names...`, which reads like an ad hoc prompt/response rather than a precise rule definition. This makes the applicable condition unclear and does not spell out broader inclusion or exclusion criteria for filename casing variations.

Vague Triggers

Low

Confidence: 80% confidence
Finding: The template includes vague example links such as `[[About auth]]` and `[[Auth flow in Project-1]]` without defining naming constraints or clarifying whether these are literal canonical titles versus informal placeholders. In a conventions document, this can blur the expected scope of acceptable link names and lead to inconsistent or unintended usage.

Natural-Language Policy Violations

Low

Confidence: 97% confidence
Finding: Lines L256, L260, L264, and L267 use Chinese text ('筛选条件') inside otherwise English documentation. This introduces a forced mixed-language experience without indicating that the document is intentionally bilingual or region-specific.

Natural-Language Policy Violations

Low

Confidence: 95% confidence
Finding: Lines L149-L151 state that all documents use English as the primary language and that Persian content must be translated or summarized in English. This is a natural-language locale policy constraint with no opt-in, alternative language support, or stated compliance justification.

Static analysis

No suspicious patterns detected.