ClawHub
Back to skill

Security audit

Upstage Document Classification

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward guide for using Upstage's remote document-classification API, with expected privacy considerations for documents sent to that service.

Install only if you are comfortable sending the documents or document URLs you classify to Upstage's API under your own Upstage account. Avoid using highly sensitive, regulated, or confidential documents unless your organization has approved that service, and review any local output path because results may persist on disk.

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
  • 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 (8)

External Transmission

Medium
Category
Data Exfiltration
Confidence
96% confidence
Finding

This code sends the document provided by the user to Upstage's external API for classification. Because documents may contain sensitive personal, financial, legal, or proprietary data, transmitting them to a third-party service is a real data-exposure risk if users are not clearly informed and consent is not obtained.

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
client = OpenAI(
    api_key=os.environ["UPSTAGE_API_KEY"],
    base_url="https://api.upstage.ai/v1/document-classification"
)

response = client.chat.completions.create(

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs the agent to create files in a system temp directory or in a user-specified output path, but it does not warn about filesystem side effects, path safety, overwrite risk, or the sensitivity of classified document outputs. In an agent setting, this can lead to unintended data persistence, writes to unsafe locations, or disclosure of sensitive document contents through generated artifacts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The examples instruct users to send document content to a third-party API but do not warn that PDFs or images may contain sensitive, regulated, or proprietary data. In a document-classification skill, this omission is material because users may reasonably test with real business documents, creating privacy, compliance, and data-governance risk.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md
client = OpenAI(
    api_key=os.environ["UPSTAGE_API_KEY"],
    base_url="https://api.upstage.ai/v1/document-classification"
)

response = client.chat.completions.create(

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 55)May include surrounding context.

md
client = OpenAI(
    api_key=os.environ["UPSTAGE_API_KEY"],
    base_url="https://api.upstage.ai/v1/document-classification"
)

response = client.chat.completions.create(

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/document-split.md (reported line 13)May include surrounding context.

md
client = OpenAI(
    api_key=os.environ["UPSTAGE_API_KEY"],
    base_url="https://api.upstage.ai/v1/document-classification"
)

response = client.chat.completions.create(

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/document-split.md (reported line 85)May include surrounding context.

md
client = OpenAI(
    api_key=os.environ["UPSTAGE_API_KEY"],
    base_url="https://api.upstage.ai/v1/document-classification"
)

response = client.chat.completions.create(

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/document-split.md (reported line 82)May include surrounding context.

curl Example (Single-Document Classification)

bash
curl -X POST "https://api.upstage.ai/v1/document-classification" \

Static analysis

No suspicious patterns detected.