Back to skill

Security audit

Audit Financial Data Extraction

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed, user-run financial report extraction helper that reads a chosen text file and writes a chosen Excel file without network access, persistence, or credential handling.

Install only if you are comfortable processing audit-report text locally with this skill. Review the Excel output path before running because an existing file at that path may be overwritten, and verify all extracted financial figures manually before using them in bids or filings.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This is a markdown file, so SQP-2 applies to omitted warnings in the skill description. The workflow and usage instructions state that the skill will process audit-report text and output an Excel file, but they do not disclose privacy/data-sensitivity considerations or caution users to verify output paths before writing files.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This markdown test-case file presents the skill content exclusively in Chinese, including the title and all test case descriptions. Under the language/locale policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified, which is not shown here.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file uses Chinese for all substantive user-facing content, which can amount to a language/locale policy violation if users are not given an opt-in or alternative language. The file does not indicate that the skill is region-specific or provide any multilingual option.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

A natural-language policy issue may exist because the skill-facing report uses only Chinese text and does not provide any user opt-in or language/locale selection. Under the stated policy, forcing a specific language without user choice can be a violation unless the locale constraint is clearly documented and justified.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

This markdown file states that the skill can output an Excel results file and perform automated data extraction and calculation, but it does not include any warning about creating files or handling potentially sensitive financial data. For markdown files, user-facing descriptions should disclose behaviors that may affect user data or system state.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

Line L17 states that the script runs normally and can perform automatic data extraction and calculation, but the provided file is a Markdown test report with no code. This is an active contradiction between the document's claim about implemented behavior and the actual contents of the file under review.

Content

No source excerpt is available for this finding.