Back to skill

Security audit

business-documents

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed business-document API integration, with sensitive document data sent to its platform as expected for creating and exporting PDFs.

Install only if you are comfortable sending the business document details you provide, such as customer information, amounts, and tax fields, to the AI Skills platform and paying the platform charges for successful create, update, or export operations. Keep the API key private and use the default API URL unless the platform operator gives you a trusted self-hosted endpoint.

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The manifest description is entirely framed in Chinese and presents the skill's usage scenario only in that language. Under the policy, language or locale restrictions should either offer user opt-in/choice or be clearly justified as region-specific; neither is stated here.

Natural-Language Policy Violations

Medium
Confidence
88% confidence
Finding
The entire behavioral rules document is written only in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking/regional context. Under the policy, a language constraint without opt-in or justification is a natural-language policy concern.

External Transmission

Medium
Category
Data Exfiltration
Content
请求示意:

```sh
curl -sS -X POST "$BASE/business-documents/document.read" \
  -H "Authorization: Bearer $BUSINESS_DOCUMENTS_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $REQUEST_UUID" \
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Natural-Language Policy Violations

Medium
Confidence
91% confidence
Finding
The file's operational instructions are entirely in Chinese, and there is no indication that the skill is region-specific or that users can opt into this language. Under the policy, forcing a specific language without user choice or justification is a natural-language policy violation.

Static analysis

No suspicious patterns detected.