Security audit

Doc Structurer

Security checks for vulnerabilities and agentic risk

Overview

This skill locally converts parsed document text into structured JSON and does not show hidden export, persistence, credential use, or destructive behavior.

Install only if you are comfortable processing the selected parsed document data locally. Review structured_results.json before passing it to Notion or calendar sync, because those later steps may store document metadata, dates, financial fields, and summaries in external services.

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
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (8)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 88% confidence
Finding: The skill describes a document-processing pipeline that reads parsed document content and produces structured outputs, and the analyzer detected file read/write capabilities, but the manifest does not declare any explicit tool scope or permissions. In a pipeline handling potentially sensitive business documents, missing scope declarations weakens least-privilege controls and can allow broader file access than users or orchestrators expect.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly states that extracted document data will be sent to Notion and calendar data may be registered in Apple Calendar, but the skill description does not warn users that potentially sensitive document contents and metadata may be stored in external services. This creates a privacy and data-governance risk because users may process contracts, government documents, invoices, or meeting notes without informed consent about downstream disclosure.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 82% confidence
Finding: The file is written as a prescriptive instruction set in Korean and does not indicate that the user may choose another language or locale. Under SQP-3, forcing a specific language without user opt-in is a natural-language policy concern unless the locale limitation is explicitly documented and justified, which is not present here.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly states that extracted document data will be forwarded to Notion for database storage and to a calendar system for event creation, but it does not require an explicit user consent or warning before those external writes occur. Because the skill processes potentially sensitive document contents, this can lead to unintended disclosure of personal, financial, or organizational data to third-party services.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The prompt is entirely written as a Korean-only operating instruction and the output schema/report format are specified in Korean, with no indication that the user may choose another language. Under the policy, forcing a specific language or locale without user opt-in is a natural-language policy violation unless the restriction is explicitly justified.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The prompt directs immediate execution of a local script against a user-supplied file path or folder with no confirmation, scope restriction, or warning about reading files and writing structured_results.json. In an agent setting, this can cause unintended processing of sensitive local data or unexpected file creation/modification based solely on user input.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 94% confidence
Finding: This Python file contains user-facing natural-language content entirely in Korean, including the module description and CLI output/help text. Under the stated policy, forcing a specific language without user opt-in is a locale/language policy issue because users are not given any alternative or configuration.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The printed completion messages and usage instructions are user-facing operational text, but they are hardcoded only in Korean. This creates a language policy concern because the script imposes a single locale on all users without offering a choice or documenting a justified regional constraint.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn

Code: suspicious.prompt_injection_instructions
Location: system-prompt.md:1