Back to skill

Security audit

expense-tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it says: it parses expense messages and writes them to a user-configured Notion database.

Install only if you are comfortable storing expense details in Notion. Use a dedicated Notion integration token shared only with the intended expense database, and review the database permissions before use.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Taint TrackingDirect Taint Flow, Variable-Mediated Taint Flow, Credential Exfiltration Chain
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (7)

Tainted flow: 'headers' from os.getenv (line 148, credential/environment) → requests.post (network output)

Critical
Category
Data Flow
Confidence
90% confidence
Finding

Credentials or environment variables flow to a network sink. This is a high-confidence indicator of credential exfiltration.

Content

Scanner excerpt · expense_tracker.py (reported line 165)May include surrounding context.

python
}
        }

        response = requests.post(
            "https://api.notion.com/v1/pages",
            headers=headers,
            json=payload,

Whitespace Padding

Medium
Category
Prompt Injection
Confidence
70% confidence
Finding

Large whitespace padding was detected (a block of blank lines or a long run of spaces). This can push injected instructions below or to the right of the visible area so a human reviewer never sees them while the agent still reads them. Manual review of the hidden content is recommended.

Content

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

md
### Required Notion Database Schema

| Property         | Type   | Notes                                                                                         |
|------------------|--------|-----------------------------------------------------------------------------------------------|
| Name             | title  | Expense description                                                                           |
| Amount           | number | Numeric value in SGD, no currency prefix                                                      |

External Transmission

Medium
Category
Data Exfiltration
Confidence
82% confidence
Finding

This code performs an external network transmission to Notion containing personal expense records. In the context of an agent skill, outbound transmission of financial activity to a third party is sensitive and should be treated as a real privacy/security concern unless clearly disclosed and authorized by the user.

Content

Scanner excerpt · expense_tracker.py (reported line 165)May include surrounding context.

python
}
        }

        response = requests.post(
            "https://api.notion.com/v1/pages",
            headers=headers,
            json=payload,

External Transmission

Medium
Category
Data Exfiltration
Confidence
82% confidence
Finding

This code performs an external network transmission to Notion containing personal expense records. In the context of an agent skill, outbound transmission of financial activity to a third party is sensitive and should be treated as a real privacy/security concern unless clearly disclosed and authorized by the user.

Content

Scanner excerpt · expense_tracker.py (reported line 165)May include surrounding context.

python
}
        }

        response = requests.post(
            "https://api.notion.com/v1/pages",
            headers=headers,
            json=payload,

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The function sends user-provided expense details, payment method, amount, and date to a third-party service without any in-function disclosure, confirmation, or consent check. In an agent/skill context, this can cause silent transmission of personal financial data to an external platform, which is a privacy and data-handling risk even though the destination is legitimate.

Content

No source excerpt is available for this finding.

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 · expense_tracker.py (reported line 166)May include surrounding context.

python
}

        response = requests.post(
            "https://api.notion.com/v1/pages",
            headers=headers,
            json=payload,
            timeout=30

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill writes user-provided expense data to an external Notion database, but the description does not clearly warn users that their chat input will be persisted remotely. This can cause unintended disclosure of personal financial information because users may treat the interaction like ephemeral chat rather than a data-writing action.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.